15 citations · 29 across the 10 of their papers we have counts for
12 papers
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
Runlin Lei, Xiaokui Xiao, Zhewei Wei
Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we…
Learning Agent-Compatible Context Management for Long-Horizon Tasks
Lu Yi, Runlin Lei, Liuyi Yao +6
LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and re…
Leveraging LLM-based agents for social science research: insights from citation network simulations
Jiarui Ji, Runlin Lei, Xuchen Pan +8
The emergence of Large Language Models (LLMs) demonstrates their potential to encapsulate the logic and patterns inherent in human behavior simulation by leveraging extensive web d…
Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
Runlin Lei, Lu Yi, Mingguo He +4
While Graph Neural Networks (GNNs) and Large Language Models (LLMs) are powerful approaches for learning on Text-Attributed Graphs (TAGs), a comprehensive understanding of their ro…
GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
Jie Peng, Jiarui Ji, Runlin Lei +3
Dynamic Text-Attributed Graphs (DyTAGs), which intricately integrate structural, temporal, and textual attributes, are crucial for modeling complex real-world systems. However, mos…
Future Link Prediction Without Memory or Aggregation
Lu Yi, Runlin Lei, Fengran Mo +3
Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel…
Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
Runlin Lei, Jiarui Ji, Haipeng Ding +4
With the rise of large language models (LLMs), there has been growing interest in Graph Foundation Models (GFMs) for graph-based tasks. By leveraging LLMs as predictors, GFMs have…
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
Jiarui Ji, Runlin Lei, Jialing Bi +6
The structural properties of naturally arising social graphs are extensively studied to understand their evolution. Prior approaches for modeling network dynamics typically rely on…
Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
Yuwei Hu, Runlin Lei, Xinyi Huang +2
Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inheren…
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
Jie Peng, Runlin Lei, Zhewei Wei
The drastic performance degradation of Graph Neural Networks (GNNs) as the depth of the graph propagation layers exceeds 8-10 is widely attributed to a phenomenon of Over-smoothing…
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
Runlin Lei, Yuwei Hu, Yuchen Ren +1
Graph Neural Networks (GNNs) excel across various applications but remain vulnerable to adversarial attacks, particularly Graph Injection Attacks (GIAs), which inject malicious nod…
EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
Runlin Lei, Zhen Wang, Yaliang Li +2
Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning. Despite their extraordinary predictive accuracy,…