Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation

TL;DR

Path-LLM introduces a novel shortest-path-based framework leveraging large language models for unified graph representation, significantly reducing training needs and improving performance on various graph tasks.

Contribution

The paper proposes a new Path-LLM model that combines shortest-path selection, path textualization, and self-supervised LLM training to learn unified graph embeddings efficiently.

Findings

Outperforms state-of-the-art methods on multiple graph tasks

Reduces training paths by over 90% on large-scale graphs

Runs up to 35 times faster than comparable approaches

Abstract

Unified graph representation learning aims to generate node embeddings, which can be applied to multiple downstream applications of graph analytics. However, existing studies based on graph neural networks and language models either suffer from the limitations of numerous training needs toward specific downstream predictions, poor generalization, or shallow semantic features. In this work, we propose a novel Path-LLM model to efficiently learn unified graph representation, which leverages a powerful large language model (LLM) to incorporate our proposed path features. Our Path-LLM framework consists of four well-designed techniques. First, we develop a new mechanism of long-to-short shortest path (L2SP) selection, which can cover key connections between different dense groups. An in-depth analysis and comparison of different path selections is conducted to justify the rationale behind our designed L2SP method. Next, we design path textualization to obtain L2SP-based training texts with key phrase selection from node text attributes. We then feed the texts into a self-supervised LLM training process to align next node/edge generation in L2SP with next token generation in causal language modeling for graph representation learning and finally extract the unified graph embeddings. We theoretically analyze the algorithm complexity of our Path-LLM approach. Extensive experiments on large-scale graph benchmarks validate the superiority of Path-LLM against state-of-the-art methods WalkLM, GraphGPT, OFA, and GraphTranslator on two classical graph learning tasks (node classification and edge validation) and one NP-hard graph query processing task (keyword search). Compared with WalkLM, our approach saves more than 90% of training paths on millions-scale graphs and runs at most 35x faster.