Name
Reasoning/Algorithms
Date & Time
Wednesday, October 25, 2023, 3:30 PM - 5:15 PM
Speakers
Rex Ying, Yale University
Bryan Perozzi, Google Research Talk Like A Graph: Encoding Graphs For Large Language Models Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.
Clayton Sanford, Columbia University
Andrej Risteski, CMU
Rajesh Jayaram, Google Research, New York Efficiency
Bryan Perozzi, Google Research Talk Like A Graph: Encoding Graphs For Large Language Models Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.
Clayton Sanford, Columbia University
Andrej Risteski, CMU
Rajesh Jayaram, Google Research, New York Efficiency
Location Name
Kline Tower: 14th Floor
Full Address
219 Prospect St
New Haven, CT 06511
United States
New Haven, CT 06511
United States
Session Type
Workshop