Selected Peer-Reviewed Publications

+ Year of Publication :
[2024] [2023] [2022] [2021] [2020] [2019] [2017] [2016] [2015] [2014] [2013] [2012] [2011] [2010] [2009] [2008] [2007] [2006] [2005] [2004] [2003] [Pre-2003]

 

2024 + PrePrints

  • Xi Fang, Weijie Xu, Fiona Anting Tan, Jiani Zhang, Ziqing Hu, Yanjun Qi, Scott Nickleach, Diego Socolinsky, Srinivasan Sengamedu, Christos Faloutsos, (2023)
    "Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey"
    LLMs, Tabular, GenAI
(Arxiv)

 

2023

  • Zhe Wang, Haozhu Wang, Yanjun Qi, (2023)
    "T3GDT: Three-Tier Tokens to Guide Decision Transformer for Offline Meta Reinforcement Learning" at RobotLearning NeurIPS 2023(NeurIPS-23)
    Deep Reinforcement Learning, Few shot meta learning
(OpenReview)
  • Zifan Xu, Haozhu Wang, Dmitriy Bespalov, Peter Stone, Yanjun Qi, (2023)
    "Latent Skill Discovery for Chain-of-Thought Reasoning" at R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models (R0-FoMo NeurIPS-23)
    GenAI, Large Language Model, Few shot Chain of Thoughts Reasoning
(Arxiv)
  • Zhe Wang, Jake Grigsby, Yanjun Qi, (2023)
    "PGrad: Learning Principal Gradients For Domain Generalization " at The Eleventh International Conference on Learning Representations (ICLR-23) (paper acceptance rate: 31.6%)
    Deep Learning, Domain Generalization
(OpenReview) (Code)
  • Arshdeep Sekhon, Hanjie Chen, Zhe Wang, Yangfeng Ji, Yanjun Qi, (2023)
    "Improving Interpretability via Explicit Word Interaction Graph Layer" at Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23) (paper acceptance rate: 19.6%) (oral presentation (Feb 10, 3.45 pm))
    Deep Learning Interpretability, Relational Learning
(Arxiv) (Code) (Talk)
  • Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Liutong Zhou, Yanjun Qi (2023)
    "Towards Building a Robust Toxicity Predictor" at The 61st Annual Meeting of the Association for Computational Linguistics (ACL-23)
    Adversarial Attack + Toxicity Content Moderation + NLP
(URL)
  • Zichen Wang*, Ryan Brand, Jared Adolf-Bryfogle, Jasleen Grewal, Yanjun Qi, Steven A. Combs, Nataliya Golovach, Rebecca Alford, Huzefa Rangwala*, and Peter M. Clark, (2023)
    "EGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose Scoring" at ACS Omega 2024, 9, 7, 7471–7479
    Geometric Deep Learning, molecule–protein interactions
(ACS URL)
  • Aman Shrivastava, Yanjun Qi, Vicente Ordonez (2023)
    "Estimating and Maximizing Mutual Information for Knowledge Distillation" In Proceeding of 2023 IEEE CVPR Workshop on FAIR, DATA EFFICIENT AND TRUSTED COMPUTER VISION (@URL)
    Represention learning + Knowledge Distillation
(Arxiv) (Code)
  • Jake Grigsby, Zhe Wang, Yanjun Qi, (2022)
    "Long-Range Transformers for Dynamic Spatiotemporal Forecasting" The 9th SIGKDD International Workshop on Mining and Learning from Time Series (MILETS23) located with the 29th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)
    Temporal Structured Input/output + Deep Learning
(Arxiv) (Code)
  • Hanyu Liu, Chengyuan Cai, Yanjun Qi (2023)
    "Expanding Scope: Adapting English Adversarial Attacks to Chinese" TrustNLP: Third Workshop on Trustworthy Natural Language Processing Colocated with the Annual Conference of the Association for Computational Linguistics (ACL 2023) (@URL)
    Adversarial Attack + NLP
(Arxiv) (Code)
  • Paola Cascante-Bonilla, Leonid Karlinsky, James Seale ,Yanjun Qi, Vicente Ordonez, (2023)
    "On the Transferability of Visual Features in Generalized Zero-Shot Learning"
    generalized zero-shot + representation learning
(Arxiv) (Code)
  • Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw and Yanjun Qi,
    "Launchpad: Learning to Schedule Using Offline and Online RL Methods" (under review)
    Cloud computing + Reinforcement Learning
(Arxiv) (Code)

 

2022

  • Zhe Wang, Jake Grigsby, Yanjun Qi, (2022)
    "ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning" at the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022) (acceptance rate: 32% = 194 out of 712 )
    Meta Learning
(Arxiv) (Code)
  • Arshdeep Sekhon, Matthew Dwyer, Yangfeng Ji and Yanjun Qi, (2022)
    "White-box Testing of NLP models with Mask Neuron Coverage" at 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 22)
    Software testing + Machine learning monitoring
(Arxiv) (Code)
  • Arshdeep Sekhon, Zhe Wang, Beilun Wang, Yanjun Qi, (2022)
    "Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge" Proceedings of the 2022 International Conference on Artificial Intelligence and Statistics (AISTATS) (acceptance rate: 29% = 492 out of 1685 )
    Relation Identification + Extra Knowledge + Graphical Model
(Arxiv) (Code)
  • Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw and Yanjun Qi, (2022)
    "RARE: Renewable Energy Aware Resource Management in Datacenters" JSSPP22 - Job Scheduling Strategies for Parallel Processing (2022)
    Cloud computing + Reinforcement Learning
(JSSPP-link) (Code)
  • Jake Grigsby, Yanjun Qi, (2022)
    "A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets"
    Offline Deep Reinforcement Learning
(Arxiv) (Code)

 

2021

  • Jack Lanchantin, Tianlu Wang, Vicente Ordonez,, Yanjun Qi, (2021)
    "General Multi-label Image Classification with Transformers" CVPR-21 (acceptance rate: 23.7%))
    Representing Structured dependency + Masked Self Training
(Arxiv) (Code)
  • Paola Cascante-Bonilla, Fuwen Tan, Yanjun Qi, Vicente Ordonez, (2021)
    "Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning" at the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) (acceptance rate: 21%))
    semi-supervised learning + curriculum learning
(Arxiv) (Code)
  • Jin Yong Yoo, Yanjun Qi, (2021)
    "Towards Improving Adversarial Training of NLP Models"2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) , (acceptance rate: 34.9%))
    Natural Language Processing + Adversarial Examples + Adversarial Training
(Arxiv) (Code)
  • Jack Lanchantin, Arshdeep Sekhon, Clint Miller, Yanjun Qi, (2021)
    "Transfer Learning for Predicting Virus-Host Protein Interactions for Novel Virus Sequences" at 2021 ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB)
  • (acceptance rate: 29%)) Link Prediction + Masked Self Training + Sequence Representation Learning Also presented at NeurIPS Covid-19 Symposium 2020 (Spotlight), Learning Meaningful Representations of Life NeurIPS Workshop (LMRL) 2020, Machine Learning in Computational Biology (MLCB) 2020 (Spotlight)
(BioArxiv) (Code)
  • Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi, Vicente Ordonez, (2021)
    "Evolving Image Compositions for Feature Representation Learning" at the The 32nd British Machine Vision Conference (BMVC-21) (acceptance rate: 36%= 437/1206))
    data augmentation + representation learning
(Arxiv) (Code)
  • Jake Grigsby, Jin Yong Yoo, Yanjun Qi, (2021)
    "Towards Automatic Actor-Critic Solutions to Continuous Control" Deep Reinforcement Learning Workshop at NeurIPS 2021
    AutoML + Deep Reinforcement Learning
(Arxiv) (Code)
  • Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi, (2021)
    "Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing" EMNLP BlackNLP Proceeding Track
    Natural Language Processing + Interpretibility + Adversarial Examples
(Arxiv) ( Code)

 

2020

  • John X. Morris, Eli Lifland, Jin Yong Yoo, Yanjun Qi, (2020)
    "TextAttack: A Framework for Adversarial Attacks in Natural Language Processing"2020 Conference on Empirical Methods in Natural Language Processing (EMNLP),
    Natural Language Processing + Opensource pytorch library + Adversarial Examples
(Arxiv) (Code)
  • John Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji, Yanjun Qi, (2020)
    "Reevaluating Adversarial Examples in Natural Language", 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP )
    Natural Language Processing + Trustworthy Evaluation + Adversarial Examples
(Arxiv) (Code)
(Old Version)
  • Jack Lanchantin, Yanjun Qi, (2020)
    "Graph Convolutional Networks for Epigenetic State Prediction Using Both Sequence and 3D Genome Data", Bioinformatics V36, S2, Pages i659–i667, (featured ECCB track (20.19%))
    Deep Graph Neural Networks + Epigenetic data analysis
(Bioinformatics) (ChromeGCN Code)
  • Derrick Blakely, Eamon Collins, Ritambhara Singh, Yanjun Qi, (2020)
    "FastSK: Fast Sequence Analysis with Gapped String Kernels” Bioinformatics V36, S2, Pages i857–i865 (featured ECCB talk track (20.19%))
    Scalable and fast string kernel for string input based classification and regression , like TFBS;
(Bioinformatics) (Code) (Talk Slide)
  • Jake Grigsby, Yanjun Qi, (2020)
    "Measuring Visual Generalization in Continuous Control from Pixels" Deep Reinforcement Learning Workshop at NeurIPS 2020
    Visual Generalization + Deep Reinforcement Learning
(Arxiv) (Code)
  • Arshdeep Sekhon, Zhe Wang, Yanjun Qi, (2020)
    "Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural Dependency Graph." ICML Graph Relational Learning Workshop
    Neural Graphical Model + Joint Optimization
(Arxiv) (Code)
  • Jin Yong Yoo, John X. Morris, Eli Lifland, Yanjun Qi, (2020)
    "Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples" EMNLP BlackNLP Proceeding Track
    Natural Language Processing + Combinatorial Search + Adversarial Examples
(Arxiv) (Benchmark Code)
  • John X. Morris, Jin Yong Yoo, Yanjun Qi, (2020)
    "TextAttack: Lessons learned in designing Python frameworks for NLP" EMNLP Workshop for Natural Language Processing Open Source Software (NLP-OSS) Proceeding Track
    Natural Language Processing + Combinatorial Search + Adversarial Examples
(Arxiv) (Code)

 

2019

  • Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi, (2019)
    "Neural Message Passing for Multi-Label Classification", The European Conference on Machine Learning (ECML 2019)
    (acceptance rate: 18%, 130 out of 734 submissions)
    Deep Graph Neural Networks+ Multi-label Classification
(Arxiv) (LAMP Code)
  • Arshdeep Sekhon, Beilun Wang, Yanjun Qi, (2019)
    "Adding Extra Knowledge in Scalable Learning of Sparse Differential Gaussian Graphical Models", Arxiv Preprint
    Gaussian Graphical Model + Structural Change + Scalable sGGM + Extra Knowledge
(BioArxiv) (PDF) (JointNets Code)
  • Jack Lanchantin, Arshdeep Sekhon, Ritambhara Singh, Yanjun Qi, (2019)
    "Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification", NeurIPS Learning Meaningful Representations of Life Workshop (LMRL)
    Deep Learning + Prototype + Matching Networks + Multi-label Classification + Genomic Sequence
(Arxiv)

 

2018

  • Beilun Wang, Arshdeep Sekhon, Yanjun Qi, (2018)
    "A fast and scalable joint estimator for integrating additional knowledge in learning multiple related sparse gaussian graphical models.", Proceedings of The 35th International Conference on Machine Learning (ICML)
    (acceptance rate: 24.9% )
    Gaussian Graphical Model + Multitask Structural Learning + Scalable sGGM + Extra Knowledge
(Link)
(Talk) (GitHub)
(Rtool)
  • Weilin Xu, David Evans, Yanjun Qi, (2018)
    "Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks", @ proceeding of the Network and Distributed System Security Symposium (NDSS)
    (acceptance rate: 15%)
    adversarial machine learning + deep learning
(Arxiv) (Poster) (TalkSlide) (AboutTool) (Tool)
  • Beilun Wang, Arshdeep Sekhon, Yanjun Qi, (2018)
    "Fast and Scalable Learning of Sparse Changes in High-Dimensional Gaussian Graphical Model Structure", Proceedings of the 21th International Conference on Artificial Intelligence and Statistics (AISTATS)
    (acceptance rate: 30% out of 645 )
    Gaussian Graphical Model + Structural Change + Scalable sGGM
(Arxiv) (Poster) (Talk) (GitHub)
(Rtool)
  • Arshdeep Sekhon, Ritambhara Singh, Yanjun Qi, (2018)
    "DeepDiff: Deep-learning for predicting Differential gene expression from histone modifications", Bioinformatics, Volume 34, Issue 17, 1 September 2018, Pages i891–i900;
    (impact factor: 5.481 ) Deep Learning + Multitasking + EpiGenomic
(Bioinformatics) (Talk)
(DeepDiff Code)
  • Travers Ching, Daniel S Himmelstein, Brett K Beaulieu-Jones, Alexandr A Kalinin, Brian T Do, Gregory P Way, Enrico Ferrero, Paul-Michael Agapow, Wei Xie, Gail L Rosen, Benjamin J Lengerich, Johnny Israeli, Jack Lanchantin, Stephen Woloszynek, Anne E Carpenter, Avanti Shrikumar, Jinbo Xu, Evan M Cofer, David J Harris, Dave DeCaprio, Yanjun Qi, Anshul Kundaje, Yifan Peng, Laura K Wiley, Marwin HS Segler, Anthony Gitter, Casey S Greene, (2018)
    "Opportunities And Obstacles For Deep Learning In Biology And Medicine", In Journal of the Royal Society Interface.
    deep learning + biomedicine
    (impact factor: 3.91 )
(bioArxiv) (Pubmed) (GitHub)
  • Ji Gao, Jack Lanchantin, Mary Lou Soffa, Yanjun Qi, (2018)
    "Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers", published in 2018 IEEE Security and Privacy Workshops (SPW)
    (acceptance rate: 28.8% =21 out of 73 )
    adversarial machine learning + deep learning + text data
(Extend ArxivV) (IEEE Version) (DeepWordBug Code)
  • In Kee Kim, Yanjun Qi, Marty Humphrey (2018)
    "CloudInsight: Utilizing a Council of Experts to Predict Future Cloud Application Workloads", @ proceeding of IEEE CLOUD
    (acceptance rate: 15% )(@the best student paper session)
    machine learning application in cloud computing
(PDF)

 

2017

  • Ritambhara Singh, Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi, (2017)
    "Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin", at the Thirty-first Annual Conference on Neural Information Processing Systems , ( (NIPS 2017) )
    deep learning + epigenomics + interpretable model + biomedical application
(Arxiv) (Talk) (Online) (AttentiveChrome Code)
(Web)

  • Beilun Wang, Ji Gao, Yanjun Qi, (2017)
    "A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Models", Proceedings of The 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (acceptance rate: 30% out of 530 )
    information fusion + Gaussian graphical model + large-scale learning
(Arxiv) (PDF) (Poster) (Online) (Code) (Rtool)
  • Beilun Wang, Ritambhara Singh, Yanjun Qi, (2017)
    "A constrained L1 minimization approach for estimating multiple Sparse Gaussian or Nonparanormal Graphical Models", (Machine Learning) Journal (2017). doi:10.1007/s10994-017-5635-7
    graphical model + interpretable model + biomedical application
(Arxiv) (PDF) (Talk) (Online) (Code) (Rtool)
  • Ritambhara Singh, Arshdeep Sekhon, Kamran Kowsari, Jack Lanchantin, Beilun Wang, Yanjun Qi (2017)
    "GaKCo: a Fast GApped k-mer string Kernel using COunting", The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) (ECML-PKDD 2017) (acceptance rate: 27% (total 104 out of 384 submissions) )
    string kernel + fast/scalable/parallel machine learning + biomedical application
(Arxiv) (PDF) (Talk) (TalkPDF) (GaKCo Code)
  • Jack Lanchantin, Ritambhara Singh, Beilun Wang, Yanjun Qi, (2017)
    "Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks", the Proceedings of Pacific Symposium on Biocomputing (PSB-17 (Talk/Proceeding))
    (Best Paper Award !) at NIPS17 workshop for Transparent and interpretable Machine Learning in Safety Critical Environments.
    deep learning + structured prediction + interpretable model + biomedical application
(PDF) (Talk) (Arxiv) (Online) (DeepMotif Code) (Data)
  • Beilun Wang, Ji Gao, Yanjun Qi, (2017)
    "A Theoretical Framework for Robustness of (Deep) Classifiers Against Adversarial Examples", the International Conference on Learning Representations , (ICLR- 2017 )
    representation learning + adversarial machine learning
(Arxiv) (Poster) (PDF)
  • Andrew Norton, Yanjun Qi, (2017)
    "Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning", The IEEE Symposium on Visualization for Cyber Security (VizSec),
    adversarial examples + visualization
(Arxiv) (ArxivV0)
(Slide) (Code)
  • Ji Gao, Beilun Wang, Zeming Lin, Weilin Xu, Yanjun Qi, (2017)
    "DeepCloak: Masking Deep Neural Network Models for Robustness against Adversarial Samples", the International Conference on Learning Representations , (ICLR-2017 )
    representation learning + adversarial machine learning
(Arxiv) (Poster) (Code)
  • Jack Lanchantin, Ritambhara Singh, Yanjun Qi, (2017)
    "Memory Matching Networks for Genomic Sequence Classification", the International Conference on Learning Representations , (ICLR-2017 )
    representation learning + genomic sequence mining
(Arxiv) (Poster)
  • Chandan Singh, Beilun Wang, Yanjun Qi, (2017)
    "A Constrained, Weighted-L1 Minimization Approach for Joint Discovery of Heterogeneous Neural Connectivity Graphs", Appeared at the NIPS 2017 workshop for Advances in Modeling and Learning Interactions from Complex Data.
    sGGM + Neuro-Imaging + Functional Connectivity
(Arxiv) (Slide) (Poster) (Code) (Rtool)
  • Muthuraman Chidambaram, Yanjun Qi,
    "Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently",
    adversarial learning + style transfer
(Arxiv) (Code)

 

2016

  • Ritambhara Singh, Jack Lanchantin, Yanjun Qi, (2016)
    "DeepChrome: Deep-learning for predicting gene expression from histone modifications", 15th European Conference on Computational Biology , (Bioinformatics (2016) 32 (17): i639-i648.)
    (impact factor: 5.481 ) deep learning + epigenomics + interpretable model + biomedical application
(PDF) (Slide) (Arxiv) (Online) (DeepChrome Code)
(Web)

  • Zeming Lin, Jack Lanchantin, Yanjun Qi, (2016)
    "MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction", the 30th AAAI Conference on Artificial Intelligence , ((AAAI-16))   (Talk / Paper acceptance rate: 26% )
    deep learning + structured prediction + biomedical application
(PDF) (Talk) (online) (Arxiv) (Code)
(Data)
  • Ritambhara Singh, Jack Lanchantin, Gabriel Robins, Yanjun Qi, (2016)
    "Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction", IEEE/ACM Transactions on Computational Biology and Bioinformatics (Journal), (TCBB)
    string kernel + transfer learning + biomedical application
(PDF) (Talk) (online) (Arxiv) (Code)
  • Feiyu Xiong; Moshe Kam ; Leon Hrebien; Beilun Wang; Yanjun Qi, (2016)
    "Kernelized Information-Theoretic Metric Learning for Cancer Diagnosis using High-Dimensional Molecular Profiling Data", ACM Transactions on Knowledge Discovery from Data (Journal), (TKDD)
    metric learning + Kernel method + biomedical application
(PDF) (Online) (Code)
(Data)
  • Ritambhara Singh, Yanjun Qi, (2016)
    "Character based String Kernels for Bio-Entity Relation Detection", the Proceedings of ACL - 15th Workshop on Biomedical Natural Language Processing , (BIONLP 2016)
    character-based representation + string kernel + text classification + biomedical application
(PDF) (Talk) (Online) (Code)
  • Jack Lanchantin, Ritambhara Singh, Zeming Lin, Yanjun Qi, (2016)
    "Deep Motif: Visualizing Genomic Sequence Classifications", the International Conference on Learning Representations , (ICLR-2016 )
    deep learning + structured prediction + interpretable model + biomedical application
(PDF) (Arxiv) (Online) (Code) (Data)
  • Beilun Wang, Ritambhara Singh, Yanjun Qi, (2016)
    "A constrained L1 minimization approach for estimating multiple Sparse Gaussian or Nonparanormal Graphical Models", the International Conference on Machine Learning , (Computational Biology Workshop )
    graphical model + interpretable model + biomedical application
(Arxiv) (Code) (Data)
  • Weilin Xu, Yanjun Qi, David Evans (2016)
    "Automatically Evading Classifiers", Proceedings of the Network and Distributed System Security Symposium, , ((NDSS-16))   (Talk / Paper acceptance rate: 60/389=15%)
    machine learning + security
(PDF) (Talk) (Code)
  • Sarah Mohamed, Nick Janus, Yanjun Qi, (2016)
    "SCODE: A Cytoscape app for supervised complex detection in protein-protein interaction graphs", (F1000Research)
    subgraph search + biomedical application
(Online) (Code) (Data)
  • Jiaqi Gong, Yanjun Qi, Myla Goldman, John Lach (2016)
    "Causality Analysis of Inertial Body Sensors for Multiple Sclerosis Diagnostic Enhancement", IEEE Journal of Biomedical and Health Informatics , , ((BHI))   (Journal Impact Factor 2.093)
    time series segmentation / casual analysi + sensor data
(Online)
  • Jiaqi Gong, Philip Asare, Yanjun Qi, John Lach (2016)
    "Piecewise Linear Dynamical Model for Action Clustering from Real-World Deployments of Inertial Body Sensors", IEEE Transactions on Affective Computing, , ((TAFFCSI))   (Journal Impact Factor 2.675)
    time series segmentation / clustering + sensor data
(Online)
  • InKee Kim, Wei Wang, Yanjun Qi and Marty Humphrey, (2016)
    "Empirical Evaluation of Workload Forecasting Techniques for Predictive Cloud Resource Scaling", IEEE (CLOUD)   (Talk / Paper acceptance rate: 15%)
    Supervised Local Learning approach + system-level data about cloud system
(PDF) (Talk)
  • Babiceanu, Mihaela; Qin, Fujun; Xie, Zhongqiu; Jia, Yuemeng; Lopez, Kevin; Janus, Nick; Facemire, Loryn; Kumar, Shailesh; Pang, Yuwei; Qi, Yanjun; Lazar, Luliana; Li, Hui, (2015)
    "Recurrent Chimeric Fusion RNAs in Non-Cancer Tissues and Cells", Nucleic Acid Research (Journal), (NAR) (Impact Factor 8.808)
    graph mining + novel biomedical application
(Online)

 

2015

  • Sarah Masud Preum, John Stankovic, Yanjun Qi (2015)
    "MAPer: A Multi-scale Adaptive Personalized Model for Temporal Human Behavior Prediction ", The 24th ACM International Conference on Information and Knowledge Management (CIKM 2015)  (long paper acceptance rate: 18% = 87/484)
    Feature learning + Time series prediction
(PDF) (Talk) (Data)
  • Ritambhara Singh; Gabriel Robins; Yanjun Qi; (2015)
    "Transfer String Kernel for Cross-Context Transcription Factor Binding Prediction", the 14th International Workshop on Data Mining in Bioinformatics (BioKDD'15)
    Sequence Labeling + Kernel + Transfer Learning
(PDF) (Talk) (online) (Arxiv) (Code)
  • Ke Wang, Yanjun Qi, Jeffrey J. Fox, Mircea R. Stan, Kevin Skadron, (2015)
    "Association Rule Mining with the Micron Automata Processor", 29th IEEE International Parallel & Distributed Processing Symposium (IPDPS15)
    Data mining + Hardware acceleration
(PDF) (Talk)
  • Oznur Tastan, Yanjun Qi, J.G. Carbonell, Judith Klein-Seetharaman, (2015)
    "Refining Literature Curated Protein Interactions Using Expert Opinions", The 20th Pacific Symposium on Biocomputing (PSB) , (PSB15)
    Crowd sourcing + Network Biology
(PDF) (Talk) (Data)
  • Ritambhara Singh; Cem Kuscu; Aaron Quinlan; Yanjun Qi; Mazhar Adli, (2015)
    "Cas9-Chromatin binding information enables more accurate CRISPR Off-target Prediction", Nucleic Acid Research (Journal), (NAR) (Impact Factor 8.808)
    sequence labeling + novel biomedical application
(Online) (PDF)
  • Jiaqi Gong, John Lach, Yanjun Qi, MD. Goldman, (2015)
    "Causal Analysis of Inertial Body Sensors for Enhancing Gait Assessment Separability towards Multiple Sclerosis Diagnosis", IEEE Body Sensor Network (BSN) 2015 ,
    Casual analysis + Temporal data
(PDF) (Talk)
  • Weilin Xu, Yanjun Qi, David Evans, (2015)
    Poster: "Automatically Evading Classifiers", 36th IEEE Symposium on Security and Privacy (SP2015)
    Secure machine learning
(PDF)
  • Chunkun Bo, Ke Wang, Yanjun Qi, Kevin Skadron (2015)
    Poster: "String kernel testing acceleration using the Micron Automata Processor", Workshop on Computer Architecture for Machine Learning
    Scaling up machine learning with hardware
(PDF)
(url)

 

2014

  • Y. He, K. Kavukcuoglu, Y. Wang, A. Szlam, Y. Qi (2014)
    "Unsupervised Feature Learning by Deep Sparse Coding", SIAM 2014 International Conference on Data Mining (SDM2014) (acceptance rate: 29% (120 out of total 389 submissions) )
    Unsupervised feature learning (Also presented and featured as the only three talks at ICLR 2014.)
(PDF) (Arxiv) (Talk)
  • Y. Qi, S. Das, R. Collobort and J. Weston (2014)
    "Deep Learning for Character-based Information Extraction", The European Conference on Information Retrieval (ECIR2014)
    Deep learning + Sequence Labeling
(PDF) (Web) (Talk)
  • J. Gong, P. Asare, J. Lach, Y. Qi, (2014)
    "Piecewise Linear Dynamical Model for Actions Clustering from Inertial Body Sensors with Considerations of Human Factors", BodyNets 2014 : 9th International Conference on Body Area Networks (BodyNets2014)
    (Best Paper Award !) Temporal Data Segmentation + sensor data + Human activity Recognition
(PDF) (Talk)
  • F. Xiong, M. Kam, L. Hrebien, and Y. Qi (2014)
    "Ranking with Distance Metric Learning for Biomedical Severity Detection", SIAM 2014 International Conference on Data Mining (SDM2014), 3rd Workshop on Data Mining for Medicine andHealthcare (DMMH)
    Distance metric learning + Biomedical Severity
(PDF)
  • S. Das, Y. Qi, P. Mitra, and L. Giles (2014)
    "Extracting Metadata from Academic Homepages using Labeled Features", SIAM 2014 International Conference on Data Mining (SDM2014) (acceptance rate: 29% (120 total 389 submissions) )
    Semi-supervised feature learning + Web text mining
(PDF) (posterSlide)
  • R. Min, S.A. Chowdhury, Y. Qi, A. Stewart, R. Ostroff (2014)
    "An integrated approach to blood-based cancer diagnosis and biomarker discovery", The 19th Pacific Symposium on Biocomputing (PSB) 19:87-98 , (PSB14)
    Supervised Feature Learning + Genomic data
(PDF)
  • I.K. Kim, J. Steele, Y. Qi and M. Humphrey, (2014)
    "Comprehensive Elastic Resource Management to Ensure Predictable Performance for Scientific Applications on Public IaaS Clouds", IEEE/ACM 7th International Conference on Utility and Cloud Computing (UCC)
    Supervised Local Learning approach + system-level data about cloud system
(PDF)
  • MR Min, X. Ning, Y. Qi, C. Cheng, A. Bonner and M. Gerstein (2014)
    "Ensemble Learning Based Sparse High-Order Boltzmann Machine for Unsupervised Feature Interaction Identification", NIPS Machine Learning for Computational Biology (MLCB) workshop
    Sparse learning + Structure Learning in Graphical Model
(PDF)

 

2013

  • R. Min and Y. Qi (2013)
    Sparse high-order boltzmann machine for identifying combinatorial interactions between transcription factors, US Patent App. 13/908,715, 2013 ,
    Learning Conditional Dependency among Variables + Network biology
(URL)
  • Y. He, Y. Qi, K. Kavukcuoglu (2013)
    Latent Factor Dependency Structure Determination, US Patent 20,130,091,081, 2013 (Granted)
    Learning Conditional Dependency among Latent Variables + Image/Text data
  • Y. Qi and B. Bai (2013)
    Document Classification with Weighted Supervized n-gram Embedding, US Patent 20,120,310,627, 2013 (Granted)
    Deep learning for n-gram embedding + Text Language data
  • X. Chen, Y. Qi and B. Bai (2013)
    System and methods for finding hidden topics of documents and preference ranking documents, US Patent 20,120,323,825 (Granted)
    Sparse Learning + Text Ranking

 

2012

  • Y. Qi, and P. Laquerre (2012)
    Retrieving Medical Records with sennamed: NEC Labs America at TREC 2012 Medical Record Track, Proceedings of the 2012 Text Retrieval Conference
    We won the 2nd place among all 82 TREC Medical Track Automatic submissions. Ranks at the 3rd place among all TREC Medical submissions (82 automatic + 6 manual)
(PDF), (bibTex)
  • Y. Qi, M. Osh, J. Weston, W. Noble (2012)
    A unified multitask architecture for predicting local protein properties, PLoS ONE (March 2012) (Impact Factor 4.411)
    Deep neural network architecture + Protein Sequence Labeling
(PDF), (Online), (bibTex), (Site) (Data)

  • Y. He, Y. Qi, K. Kavukcuoglu, H. Park (2012)
    "Learning the Dependency Structure of Latent Factors", NIPS 2012(online) (acceptance rate: 25% (=370/1467 submissions) )
    Latent Factor Model + Sparse Gaussian Graphical Model
    *ERRATUM*: the equation under Eq(13) has missed B^T. Issue fixed in the version here.
(PDF) (bibTex) (Talk) (Poster) (Code)
  • Y. Qi  (2012) 
    Random Forest for Bioinformatics, Invited chapter in Springer book: "Ensemble Learning: Methods and Applications" -> (book OnlineLink),
    Review of recent efforts related to random forest in bioinformatics.
(Chapter-PDF) (bibTex) (Code)
  • D. Bespalov, Y. Qi, B. Bai, A. Shokoufandeh, (2012)
    "Sentiment Classification with Supervised Sequence Encoder",The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) (ECML2012) (acceptance rate: 23% (total 443 submissions) )
    Deep Learning + ngram embedding + sentiment classification.
    *ERRATUM*: Old data sharing site "http://mst.cs.drexel.edu/datasets/ECML2012" not working anymore. Now we put data @ (DataSharing)
(PDF) (bibTex) (Talk) (Data)
  • D. Bespalov, Y. Qi, B. Bai, A. Shokoufandeh, (2012)
    "Large-scale Image Classification Using Supervised Spatial Encoder",the twenty-first conference of the International Association for Pattern Recognition (ICPR2012) (acceptance rate: )
    Deep Learning + fast large-scale spatial pooling + image classification.
(PDF) (bibTex) (Talk)
  • Ilia Nouretdinov, Alex Gammerman, Y. Qi, J. Klein-Seetharaman (2012)
    "Determining confidence of predicted interactions between HIV-1 and human proteins using conformal method", 17th Pacific Symposium on Biocomputing (PSB) Jan 2012,
    Conformal Prediction + Network biology
(PDF)(bibTex)
  • D. Bespalov, Y. Qi, B. Bai, (2012)
    Sentiment Classification Based on Supervised Latent n-gram Analysis, US Patent 20,120,253,792, 2012 (Granted)
    Deep Learning + ngram Embedding + Sentiment Classification
(bibTex)

 

2011

  • Y. Qi , W. Noble  (2011) 
    Protein Interaction Networks: Protein Domain Interaction and   Protein Function Prediction , Invited chapter in book: Handbook of Computational Statistics: Statistical Bioinformatics -> (book OnlineLink),
    Network biology + Relational data mining
(Chapter-PDF) (bibTex)
  • X. Chen, Y. Qi, B. Bai, Q. Lin, J.G. Carbonell (2011)
    "Sparse Latent Semantic Analysis", SIAM 2011 International Conference on Data Mining (SDM2011) (acceptance rate: 25% = 86/343)
    Spare Learning + Factor Model + Text topic modeling
(PDF) (Talk) (bibTex) (Code)
  • X. Ning, Y. Qi (2011)
    "Semi-Supervised Convolution Graph Kernels for Relation Extraction", SIAM 2011 International Conference on Data Mining (SDM2011) (acceptance rate: 25% = 86/343)
    Graph Kernel + Semi-supervised Learning + Relation Extraction from Text
(PDF) (bibTex) (Talk)
  • D. Bespalov, B. Bai, Y. Qi, A. Shokoufandeh (2011)
    "Sentiment Classification Based on Supervised Latent n-gram Analysis",20th ACM Conference on Information and Knowledge Management (CIKM2011) (acceptance rate: as full paper 15% out of 917)
    Deep Learning + Latent ngram embedding + Sentiment classification
    *ERRATUM*: Old data sharing site "http://mst.cs.drexel.edu/datasets/CIKM2011" not working anymore. Now we put data @ (DataSharing)
(PDF) (bibTex) (Talk) (Data)
  • Y. He, K. Kavukcuoglu, Y. Qi, H. Park (2011)
    "Structured Latent Factor Analysis",NIPS 2011 Workshop: Challenges in Learning Hierarchical Models: Transfer Learning and Optimization
    Sparse Gaussian Graphical Modeling among Latent Factors
(online)(PDF)
  • Y. Qi, X. Ning, P. Kuksa, B. Bai, (2011)
    Systems and methods for semi-supervised relationship extraction, US Patent App. 13/078,985, 2011 / (US Patent 8,874,432, 2014 Granted)
    Semi-supervised learning + Relationship extraction
(bibTex)

 

2010

  • Y. Qi, O.Tastan, J. Carbonell, J. Klein-Seetharaman, J. Weston (2010)
    "Semi-Supervised Multi-Task Learning for Predicting Interactions between HIV-1 and Human Proteins", Bioinformatics 2010 (Impact Factor 4.328) (acceptance rate of ECCB10: 17% = 36/215)
    Multi-task learning + Relational data + Network biology
(PDF) (Online)(Talk) (bibTex) (Code) (Data)
  • P. Kuksa,  Y. Qi (2010) 
    "Semi-Supervised Bio-Named Entity Recognition with Word-Codebook Learning" "SDM2010 (regular paper acceptance rate: 23% = 82/351)
    Feature learning + Information extraction
(PDF) (bibTex)
  • P. Kuksa, Y. Qi, B. Bai, R. Collobert, J.Weston, V. Pavlovic, X. Ning (2010)
    "Semi-Supervised Abstraction-Augmented String Kernel for Multi-Level Bio-Relation Extraction", ECML PKDD 2010 ( European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ), (acceptance rate of ECML10: 16.7% = 110/658)
    Semi-supervisions + Mismatch string kernel framework.
(PDF)(Talk) (bibTex)
  • X. Chen, Y. Qi, B. Bai, Q. Lin, J.G. Carbonell (2010)
    "Sparse Latent Semantic Analysis", NIPS Workshop on Practical Application of Sparse Modeling: Open Issues and New Directions (2010)
    Sparse learning + Latent semantic analysis + Text data
(PDF)
  • X. Chen, B. Bai, Y. Qi, Q. Lin, J. Carbonell,(2010)
    "Learning Preferences using Millions of Features by Enforcing Sparsity" IEEE ICDM 2010 (short paper acceptance rate: 19% = (72+83)/797 )
    Sparse learning + Text ranking + Feature learning
(PDF)
(Talk) (bibTex)

 

2009

  • Y. Qi, P. Kuksa, R. Collobert, K. Sadamasa, K. Kavukcuoglu, J. Weston,(2009)
    "Semi-Supervised Sequence Labeling with Self-Learned Feature" IEEE ICDM 2009 (regular paper acceptance rate: 9% = 70/786)
    Feature learning + Semi-supervised learning + Sequence labeling
(PDF)
(Talk) (bibTex)
  • Y. Qi, R. Collobert, P. Kuksa, K. Kavukcuoglu, J. Weston,(2009)
    "Combining Labeled and Unlabeled Data for Word-Class Distribution" CIKM 2009  (short paper acceptance rate: 20% = (171 + 123)/847)
    Feature learning + Semi-supervised learning + Sequence labeling
(PDF)
(bibTex)
  • Y. Qi, HK. Dhiman, et al, Z. Bar-Joseph, J. Klein-Seetharaman,(2009)
    "Systematic prediction of human membrane receptor interactions",x (PROTEOMICS 2009, 9, 5243-5255 (Impact Factor 5.479)
    Supervised Information integraion + Network biology + Experimental design
(URL) (Talk) (bibTex) (Code)
(Data) (Web)
  • O. Tastan, Y. Qi, J.G. Carbonell, J. Klein-Seetharaman, (2009);
    Prediction of Interactions between HIV-1 and Human Proteins by Information Integration , Pacific Symposium on Biocomputing 14: (PSB-2009 Jan. 2009
    Supervised Information integraion + Network biology
(PDF) (Talk) (bibTex) (Web)
(Data)
  • B. Bai, J.Weston. D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, C.  Cortes, M Mohri,(2009)
    "Polynomial Semantic Indexing"; NIPS 2009 (acceptance rate: 23% = 263/1105)
    Deep learning + Feature representation learning + Text ranking
(PDF) (bibTex)
  • B. Bai, J.Weston. D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, O. Chapelle, Kilian Weinberger, (2009)
    "Supervised Semantic Indexing", CIKM 2009 (regular paper acceptance rate: 15% = 123/847)
    Deep learning + Feature representation learning + Text ranking
(PDF)(bibTex)
  • B. Bai, J.Weston. D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, O. Chapelle, Kilian Weinberger, (2009)
    "Learning to Rank with (a Lot of) Word Features", the special issue on Learning to Rank of the Information Retrieval Journal.
    Deep learning + Feature representation learning + Text ranking
(PDF)(bibTex)
  • B. Bai, J.Weston. D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, O. Chapelle, Kilian Weinberger,(2009)
    "Learning to Rank with Low Rank", SIGIR 09 workshop: Learning to Rank for Information Retrieval
    Deep learning + Feature representation learning + Text ranking

 

2008

  • Y. Qi, (2008) Learning of Protein Interaction Networks. Ph.D. Dissertation (also CMU Technical Report: CMU-LTI-08-06), Carnegie MellonUniversity,  School of Computer Science, May 2008
    (Dissertation Committee: Ziv Bar-Joseph, Judith Klein-Seetharaman, Christos Faloutsos, Jaime Carbonell, Baldo Oliva)
    Supervised Information integraion + Structured Prediction + Network biology
(PDF) (Talk) (bibTex)
  • Y. Qi, F. Balem, C. Faloutsos, J. Klein-Seetharaman, Z. Bar-Joseph, (2008)
    Protein Complex Identification by Supervised Graph Clustering , Bioinformatics 2008, 24(13), i250-i268 (The 16th Annual International Conference Intelligent Systems for Molecular Biology (ISMB), July 2008, (Impact Factor 4.328) (acceptance rate of ISMB08: 17% = 49/292)
    Supervised Information integraion + Structured Prediction + Network biology
(Online)(PDF)
(Talk) (bibTex) (Code)
(Web)
(Data)
  • L. Pena-Castillo, et al, Y. Qi, et al, F.P. Roth,(2008)
    A Critical Assessment of M. Musculus Gene Function Prediction using Integrated Genomic Evidence ,  Genome Biology , 9(S1):S2, June 2008 (Impact Factor 6.15)
    Supervised Information integraion + Structured Prediction + Hierarchical Output
(Online) (bibTex)
  • H. Nozawa,G. Howell, S. Suzuki, Q. Zhang, Y. Qi, J. Klein-Seetharaman, A. Wells, J.R. Grandis, S.M. Thomas,(2008)
    Combined inhibition of PLC-1 and c-Src abrogates Epidermal Growth Factor Receptor-mediated head and neck squamous cell carcinoma invasion , Clinical Cancer Research, 14:4336-43,  2008 (Impact Factor 6.488)
    Network biology
(online) (bibTex)

 

2007

  • Y. Qi, J. Klein-Seetharaman, Z. Bar-Joseph, (2007)
    "A mixture of feature experts approach for protein-protein interaction prediction", BMC Bioinformatics 8(S10) S6, 2007 (Impact Factor 3.78)
    Supervised Information integraion + Structured Prediction + Network biology
(Online) (PDF) (bibTex) (SWeb)

 

2006

  • Y. Qi, Z. Bar-Joseph, J. Klein-Seetharaman,(2006) 
    "Evaluation of different biological data and computational classification methods for use in protein interaction prediction", , PROTEINS: Structure, Function, and Bioinformatics. 63(3):490-500. 2006 (Impact Factor 3.39)
    Supervised Information integraion + Structured Prediction + Network biology
((Online)) (PDF)) ((bibTex)) (Code) ((SWeb)

 

2005

  • Y. Qi, J. Klein-Seetharaman, Z. Bar-Joseph, (2005)
    "A mixture of experts approach for protein-protein interaction prediction", Proceedings of Neural Information Processing Systems (NIPS): The workshop on Computational Biology and the Analysis of Heterogeneous Data, Dec 2005.
    Supervised Information integraion + Structured Prediction + Network biology
(PDF), (talk PDF)(bibTex) (SWeb)
  • Y. Qi, J. Klein-Seetharaman, Z. Bar-Joseph, (2005)
    Random Forest Similarity for Protein-Protein Interaction Prediction from Multiple source ,Pacific Symposium on Biocomputing 10: (PSB 2005) Jan. 2005.
    Supervised Information integraion + Structured Prediction + Network biology
(PDF) (bibTex) (SWeb)

 

2004

  • A.G. Hauptmann, J. Gao, R. Yan, Y. Qi and J. , Yang, (2004)
    Automated Analysis of Nursing Home Observations , IEEE Pervasive Computing, Special Issue on Pervasive Computing for Successful Aging, 3(2):15-21, April-June, 2004
    Temporal data segmentation + Supervised learning + Human activity Recognition
(PDF) (bibTex)

 

2003

  • Y.Qi, A.Hauptman, T. Liu, (2003)
    "Supervised Classification for Video Shot Segmentation",  Proceeding of 2003 IEEE International Conference on Multimedia & Expo (ICME 2003), July 2003, Baltimore MD, USA.  
    Temporal data segmentation + Supervised learning
(PDF) (Talk) (bibTex)

 

Before 2003

  • Jin, R. ,Y. Qi, Hauptman,A.,(2002) 
    Probabilistic Model for Camera Zoom Detection , Proceedings of  the sixteenth conference of the International Association for Pattern Recognition (ICPR 2002 Quebec City, Canada August 11-15,2002
    UnSupervised learning + Pattern Mining in Video + density estimation + EM
(PDF) (bibTex)
  • Hauptmann, A., R.Yan, Y.Qi, Jin, R., M.Christel, M.Derthick,M.-Y.Chen, R.Baron, W.H.Lin, and T.D.Ng,(2002) 
    "Video Classification and Retrieval with the Informedia Digital Video Library System", the Eleventh Text Retrieval Conference (TREC-2002), Nov 2002 
    Supervised information integration + Video retrieval
(bibTex)
  • Hauptmann, A., Jin, R., N. Papernick, D. Ng, Y. Qi, Houghton, RThornton, S. (2001)
    Video Retrieval with the Informedia Digital Video Library System, Proceedings of the Tenth Text Retrieval Conference (TREC-2001), Nov 2001
    Supervised information integration + Video retrieval
(bibTex)

Back to top

Success is not final, failure is not fatal: it is the courage to continue that counts. --- Winston Churchill