18 papers
Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting
Peyman Baghershahi, Sourav Medya
Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks. However, existing approaches are predominantly supervised, r…
RIDGECUT: Learning Graph Partitioning with Rings and Wedges
Qize Jiang, Angelo Zangari, Linsey Pang +7
Reinforcement learning (RL) has shown promise for combinatorial optimization problems on graphs by learning heuristics that generalize across instances. However, effectively incorp…
Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning
Fangxin Wang, Peyman Baghershahi, Langzhou He +3
Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for of…
Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
Md Aminul Islam, Ahmed Sayeed Faruk, Sourav Medya +1
Collaborative filtering (CF) models based on graph neural networks (GNNs) achieve strong performance in recommender systems by propagating user-item signals over interaction graphs…
GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
Peyman Baghershahi, Fangxin Wang, Debmalya Mandal +1
Conformal prediction (CP) provides a distribution-free approach to uncertainty quantification with finite-sample guarantees. However, applying CP to graph neural networks (GNNs) re…
Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models
Angelo Zangari, Peyman Baghershahi, Sourav Medya
Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structu…