Harry Shomer

ladybird.jpg

I’m a tenure-track Assistant Professor in the Department of Computer Science & Engineering (CSE) at the University of Texas at Arlington. Before that, I earned my PhD in CSE from Michigan State University in 2025 under Dr. Jiliang Tang and my B.S in CS at CUNY – Brooklyn College in 2019. My work has been published at top conference including NeurIPS, ICLR, KDD, EMNLP, TheWebConf, ACL, and CIKM. I have received multiple awards and honors including the INNS Doctoral Dissertation Runner-up Award, UT Rising STARs award, NRT-IMPACTS fellowship, and top reviewer awards at ICML’25/26 and NeurIPS’25.

My research has focused on data mining and machine learning, with a focus on machine learning on graphs. Some of the topics in this area that I’m currently interested in, include: graph generation, link prediction, graph foundation models, and graph RAG.

News

Jun 03, 2026 I received the INNS Doctoral Dissertation Runner-up Award
May 17, 2026 One paper accepted by KDD! [pdf]
May 11, 2026 One REU project “Understanding and Enhancing Inductive Link Predictors on Graphs” got selected for departmental support. Thank you CSE@UTA and the CRA UR2PhD program.
Mar 11, 2026 New preprint - “Are Expressive Encoders Necessary for Discrete Graph Generation?” [pdf]
Jan 12, 2026 One paper accepted by TheWebConf! [pdf]
Nov 07, 2025 We will be giving a tutorial on “Democratizing RAGs with Structured Knowledge” at WSDM’26
Oct 13, 2025 New preprint on a unified framework for retrieval+generation on graphs [pdf]
Oct 01, 2025 New preprint on iterative retrieval for GraphRAG [pdf]

Selected Publications

  1. NeurIPS’23
    Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
    Harry Shomer*, Juanhui Li*, Haitao Mao, and 5 more authors
    In Advances in Neural Information Processing Systems, 2023
    PDF
  2. KDD’25
    Towards Understanding Link Predictor Generalizability Under Distribution Shifts
    Harry Shomer*, Jay Revolinsky*, and Jiliang Tang
    In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025
    PDF
  3. KDD’24
    LPFormer: An Adaptive Graph Transformer for Link Prediction
    Harry Shomer, Yao Ma, Haitao Mao, and 3 more authors
    In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
    PDF