257 citations · 1.2k across the 74 of their papers we have counts for
8 papers · 1 filter
GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
Jiaji Ma, Puja Trivedi, Danai Koutra
Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with G…
Random Search Neural Networks for Efficient and Expressive Graph Learning
Michael Ito, Danai Koutra, Jenna Wiens
Random walk neural networks (RWNNs) have emerged as a promising approach for graph representation learning, leveraging recent advances in sequence models to process random walks. H…
Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion
Donald Loveland, Yao-An Yang, Danai Koutra
Learning on text-attributed graphs has motivated the use of Large Language Models (LLMs) for graph learning. However, most fusion strategies are applied uniformly across all nodes…
AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
Mingdai Yang, Nurendra Choudhary, Jiangshu Du +4
Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-ex…
On the Role of Weight Decay in Collaborative Filtering: A Popularity Perspective
Donald Loveland, Mingxuan Ju, Tong Zhao +2
Collaborative filtering (CF) enables large-scale recommendation systems by encoding information from historical user-item interactions into dense ID-embedding tables. However, as e…
Learning Laplacian Positional Encodings for Heterophilous Graphs
Michael Ito, Jiong Zhu, Dexiong Chen +2
In this work, we theoretically demonstrate that current graph positional encodings (PEs) are not beneficial and could potentially hurt performance in tasks involving heterophilous…