Research

My research interests broadly lie in graphs, graph mining and algorithms, machine learning on graphs, and data science.

Publications

2026

  1. TMLR
    Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting
    Peyman Baghershahi and Sourav Medya
    Transactions on Machine Learning Research, 2026
    Link
  2. ACL
    From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
    Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, and Sourav Medya
    In The Association for Computational Linguistics, 2026
    Link
  3. ACL Findings
    Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models
    Angelo Zangari, Peyman Baghershahi, and Sourav Medya
    In Findings of the Association for Computational Linguistics, 2026
    Link
  4. KDD
    RIDGECUT: Learning Graph Partitioning with Rings and Wedges
    Qize Jiang, Angelo Zangari, Linsey Pang, Alice Gatti, Mahima Aggarwal, Giovanna Vantini, Xiaosong Ma, Weiwei Sun, Sourav Medya, and Sanjay Chawla
    In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2026
    Link
  5. ICLR
    Learning Exposure Mapping Functions for Inferring Heterogeneous Peer Effects
    Shishir Adhikari, Sourav Medya, and Elena Zheleva
    In International Conference on Learning Representations, 2026
    Link
  6. AAAI
    SMART: A Surrogate Model for Predicting Application Runtime in Dragonfly Systems
    Xin Wang, Pietro Lodi Rizzini, Sourav Medya, and Zhiling Lan
    In AAAI Conference on Artificial Intelligence, 2026
    Link

2025

  1. NeurIPS
    Preference-driven Knowledge Distillation for Few-shot Node Classification
    Xing Wei, Chunchun Chen, Rui Fan, Xiaofeng Cao, Sourav Medya, and Wei Ye
    In Neural Information Processing Systems, 2025
    Link
  2. EMNLP Findings
    DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding
    Zhu Wang, Homaira Huda Shomee, Sathya N. Ravi, and Sourav Medya
    In Empirical Methods in Natural Language Processing, 2025
    Link
  3. EMNLP Industry
    LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
    Weizhi Zhang, Liangwei Yang, Wooseong Yang, Henry Peng Zou, Yuqing Liu, Ke Xu, Sourav Medya, and Philip S. Yu
    In Empirical Methods in Natural Language Processing, 2025
    Link
  4. ICML
    COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
    Gregoire Fournier and Sourav Medya
    In International Conference on Machine Learning, 2025
    Link
  5. ACL
    Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach
    Rochana Chaturvedi, Peyman Baghershahi, Sourav Medya, and Barbara Di Eugenio
    In The 63rd Annual Meeting of the Association for Computational Linguistics, 2025
    Link
  6. ACL
    A Survey on Patent Analysis: From NLP to Multimodal AI
    Homaira Huda Shomee, Zhu Wang, Sathya N. Ravi, and Sourav Medya
    In The 63rd Annual Meeting of the Association for Computational Linguistics, 2025
    Link
  7. ICLR
    BANGS: Game-theoretic Node Selection for Graph Self-Training
    Fangxin Wang, Kay Liu, Sourav Medya, and Philip S. Yu
    In International Conference on Learning Representations, 2025
    Link
  8. WWW
    Fact-based Counter Narrative Generation to Combat Hate Speech
    Brian Wilk, Homaira Huda Shomee, Suman Kalyan Maity, and Sourav Medya
    In The Web Conference, 2025
    Link
  9. TIST
    GCFExplainer: Global Counterfactual Explainer for Graph Neural Networks
    Zexi Huang, Mert Kosan, Sourav Medya, Sayan Ranu, and Ambuj Singh
    ACM Transactions on Intelligent Systems and Technology, 2025
    Note: Conference version appeared in WSDM’23
  10. CHI LBW
    How Older Adults Communicate their Technology Problems: Challenges and Design Opportunities
    Hasti Sharifi, Homaira Huda Shomee, Sourav Medya, and Debaleena Chattopadhyay
    In Conference on Human Factors in Computing Systems, 2025
    Link

2024

  1. NeurIPS
    GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
    Burouj Armgaan, Manthan Dalmia, Sourav Medya, and Sayan Ranu
    In Thirty-eighth Conference on Neural Information Processing Systems, 2024
  2. NeurIPS
    IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
    Homaira Huda Shomee, Zhu Wang, Sathya N. Ravi, and Sourav Medya
    In Thirty-eighth Conference on Neural Information Processing Systems, 2024
    Link
  3. EMNLP
    An Experimental Analysis on Evaluating Patent Citations
    Rabindra Nath Nandi, Suman Kalyan Maity, Brian Uzzi, and Sourav Medya
    In Empirical Methods in Natural Language Processing, 2024
    Link
  4. TMLR
    Uncertainty in Graph Neural Networks: A Survey
    Fangxin Wang, Yuqing Liu, Kay Liu, Yibo Wang, Sourav Medya, and Philip S. Yu
    Transactions on Machine Learning Research, 2024
    Link
  5. KDD
    NeuroCUT: A Neural Approach for Robust Graph Partitioning
    Rishi Shah, Krishnanshu Jain, Sahil Manchanda, Sourav Medya, and Sayan Ranu
    In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2024
    Link
  6. TMLR
    InduCE: Inductive Counterfactual Explanations for Graph Neural Networks
    Samidha Verma, Burouj Armgaan, Sourav Medya, and Sayan Ranu
    Transactions on Machine Learning Research, 2024
    Link
  7. WWW
    Game-theoretic Counterfactual Explanation for Graph Neural Networks
    Chirag P. Chhablani, Sarthak Jain, Akshay Channesh, Ian A. Kash, and Sourav Medya
    In The Web Conference, 2024
    Link
  8. ICLR
    GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
    Mert Kosan, Samidha Verma, Burouj Armgaan, Khushbu Pahwa, Ambuj Singh, Sourav Medya, and Sayan Ranu
    In International Conference on Learning Representations, 2024
    Link
  9. AAAI
    DGCLUSTER: A Neural Framework For Attributed Graph Clustering via Modularity Maximization
    Aritra Bhowmick, Mert Kosan, Zexi Huang, Ambuj Singh, and Sourav Medya
    In AAAI Conference on Artificial Intelligence, 2024
    Link
  10. AAAI
    COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems
    Hao Tian, Sourav Medya, and Wei Ye
    In AAAI Conference on Artificial Intelligence, 2024
    Link
  11. SMC
    Incorporating Heterophily into Graph Neural Networks for Graph Classification
    Jiayi Yang, Sourav Medya, and Wei Ye
    In IEEE International Conference on Systems, Man, and Cybernetics, 2024
    Link
  12. GLSVLSI
    DETECTive: Machine Learning-driven Automatic Test Pattern Prediction for Faults in Digital Circuits
    Vincenzo Petrolo, Sourav Medya, Mariagrazia Graziano, and Debjit Pal
    In Great Lakes Symposium on VLSI, 2024
    Link
  13. DATE
    VeriBug: An Attention-based Framework for Bug-Localization in Hardware Designs
    Giuseppe Stracquadanio, Sourav Medya, Stefano Quer, and Debjit Pal
    In Design, Automation and Test in Europe Conference, 2024
    Link
  14. HCXAI@CHI
    Design Requirements for Human-Centered Graph Neural Network Explanations
    Pantea Habibi, Peyman Baghershahi, Sourav Medya, and Debaleena Chattopadhyay
    In CHI Workshop on Human-Centered Explainable AI, 2024

2023

  1. NeurIPS
    Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
    Zhu Wang, Sourav Medya, and Sathya N. Ravi
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
    Link
  2. A Survey on Explainability of Graph Neural Networks
    Jaykumar Kakkad, Jaspal Jannu, Kartik Sharma, Charu Aggarwal, and Sourav Medya
    IEEE Data Engineering Bulletin, 2023
    Link
  3. AAAI
    Task and Model Agnostic Adversarial Attack on Graph Neural Networks
    Kartik Sharma, Samidha Verma, Sourav Medya, Sayan Ranu, and Arnab Bhattacharya
    In Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
    Link
  4. WSDM
    Global Counterfactual Explainer for Graph Neural Networks
    Zexi Huang, Mert Kosan, Sourav Medya, Sayan Ranu, and Ambuj Singh
    In International Conference on Web Search and Data Mining, 2023
    Among Top 10 Papers (Invited to TIST Special Issue); Best Paper Award, Machine Learning on Graphs (MLoG) Workshop at WSDM’23
    Link
  5. AAMAS
    Feature-based Individual Fairness in Clustering
    Debajyoti Kar, Mert Kosan, Debmalya Mandal, Sourav Medya, Arlei Silva, Palash Dey, and Swagato Sanyal
    In International Conference on Autonomous Agents and Multiagent System, 2023
    Link
  6. DLG-AAAI
    Event Detection on Dynamic Graphs
    Mert Kosan, Arlei Silva, Sourav Medya, Brian Uzzi, and Ambuj Singh
    In AAAI Workshop on Deep Learning on Graphs: Methods and Applications, 2023
    Link

2022

  1. NeurIPS
    GREED: A Neural Framework for Learning Graph Distance Functions
    Rishabh Ranjan, Siddharth Grover, Sourav Medya, Venkatesan Chakaravarthy, Yogish Sabharwal, and Sayan Ranu
    In Thirty-sixth Conference on Neural Information Processing Systems, 2022
    Link
  2. WWW
    An Exploratory Study of Stock Price Movements from Earnings Calls
    Sourav Medya, Mohammad Rasoolinejad, Yang Yang, and Brian Uzzi
    In The Web Conference, 2022
    Link PDF
  3. Investigating variable importance in ground-level ozone formation with supervised learning
    Yu-Wen Chen, Sourav Medya, and Yi-Chun Chen
    Atmospheric Environment, 2022
    Link

2021

  1. SIGKDD Explorations
    Meta-Learning with Graph Neural Networks: Methods and Applications
    Debmalya Mandal, Sourav Medya, Brian Uzzi, and Charu Aggarwal
    ACM SIGKDD Explorations Newsletter, 2021
    Link
  2. AAMAS
    Network Robustness via Global k-cores
    Palash Dey, Suman Kalyan Maity, Sourav Medya, and Arlei Silva
    In International Conference on Autonomous Agents and Multiagent System, 2021
    Link
  3. WSDM
    Balance Maximization in Signed Networks via Edge Deletions
    Kartik Sharma, Iqra Altaf Gillani, Sourav Medya, Sayan Ranu, and Amitabha Bagchi
    In International Conference on Web Search and Data Mining, 2021
    Link
  4. AIMOCC
    Investigating Ground-level Ozone Formation: A Case Study in Taiwan
    Yu-Wen Chen, Sourav Medya, and Yi-Chun Chen
    In ICLR Workshop on AI: Modeling Oceans and Climate Change, 2021
    Link

2020

  1. NeurIPS
    GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs
    Sahil Manchanda, Akash Mittal, Anuj Dhawan, Sourav Medya, Sayan Ranu, and Ambuj Singh
    In Thirty-fourth Conference on Neural Information Processing Systems, 2020
    Link
  2. TKDE
    Approximate Algorithms for Data-driven Influence Limitation
    Sourav Medya, Arlei Silva, and Ambuj Singh
    IEEE Transactions on Knowledge and Data Engineering, 2020
    Link PDF
  3. IJCAI
    A Game Theoretic Approach For Core Resilience
    Sourav Medya, Tianyi Ma, Arlei Silva, and Ambuj Singh
    In International Joint Conference on Artificial Intelligence, 2020
    Previously appeared as Extended Abstract in AAMAS, 2020
    Link
  4. AAMAS
    A Game Theoretic Approach For k-Core Minimization
    Sourav Medya, Tianyi Ma, Arlei Silva, and Ambuj Singh
    In International Conference on Autonomous Agents and Multiagent System, 2020
    PDF
  5. AAMAS
    Manipulating Node Similarity Measures in Networks
    Palash Dey and Sourav Medya
    In International Conference on Autonomous Agents and Multiagent System, 2020
    Invited to JAAMAS Special Issue (AAMAS Top Papers)
    Link

2019

  1. AAMAS
    Covert Networks: How Hard is It to Hide?
    Palash Dey and Sourav Medya
    In International Conference on Autonomous Agents and Multiagent System, 2019
    Link

2018

  1. VLDB
    Noticeable Network Delay Minimization via Node Upgrades
    Sourav Medya, Jithin Vachery, Sayan Ranu, and Ambuj Singh
    In International Conference on Very Large Data Bases, 2018
    Link PDF
  2. TKDE
    Making a Small World Smaller: Path Optimization in Networks
    Sourav Medya, Petko Bogdanov, and Ambuj Singh
    IEEE Transactions on Knowledge and Data Engineering, 2018
    Link PDF
  3. SDM
    Group Centrality Maximization via Network Design
    Sourav Medya, Arlei Silva, Ambuj Singh, Prithwish Basu, and Anantharam Swami
    In SIAM International Conference on Data Mining, 2018
    PDF

2017

  1. IM
    Predictive Modeling and Scalability Analysis for Large Graph Analytics
    Sourav Medya, Ludmila Cherkasova, and Ambuj Singh
    In IFIP/IEEE International Symposium on Integrated Network Management, 2017
    PDF

2016

  1. ICDM
    Towards Scalable Network Delay Minimization
    Sourav Medya, Petko Bogdanov, and Ambuj Singh
    In IEEE International Conference on Data Mining, 2016
    PDF
  2. ICPE
    Towards Performance and Scalability Analysis of Distributed Memory Programs on Large-Scale Clusters
    Sourav Medya, Ludmila Cherkasova, Guilherme Magalhaes, Kivanc Ozonat, Chaitra Padmanabha, Jiban Sarma, and Imran Sheikh
    In ACM/SPEC International Conference on Performance Engineering, 2016
    PDF