HIGHT: Hierarchical Graph Tokenization for Graph-Language Alignment

• URL: http://arxiv.org/abs/2406.14021v1
• Date: Thu, 20 Jun 2024 06:37:35 GMT
• Title: HIGHT: Hierarchical Graph Tokenization for Graph-Language Alignment
• Authors: Yongqiang Chen, Quanming Yao, Juzheng Zhang, James Cheng, Yatao Bian,
• Abstract summary: We propose a novel strategy called HIerarchical GrapH Tokenization (HIGHT) to improve the graph perception of large language models (LLMs) HIGHT employs a hierarchical graph tokenizer that extracts and encodes the hierarchy of node, motif, and graph levels of informative tokens to improve the graph perception of LLMs. Experiments on 7 molecule-centric benchmarks confirm the effectiveness of HIGHT in reducing hallucination by 40%, as well as significant improvements in various molecule-language downstream tasks.
• Score: 41.75926736949724
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recently there has been a surge of interest in extending the success of large language models (LLMs) to graph modality, such as social networks and molecules. As LLMs are predominantly trained with 1D text data, most existing approaches adopt a graph neural network to represent a graph as a series of node tokens and feed these tokens to LLMs for graph-language alignment. Despite achieving some successes, existing approaches have overlooked the hierarchical structures that are inherent in graph data. Especially, in molecular graphs, the high-order structural information contains rich semantics of molecular functional groups, which encode crucial biochemical functionalities of the molecules. We establish a simple benchmark showing that neglecting the hierarchical information in graph tokenization will lead to subpar graph-language alignment and severe hallucination in generated outputs. To address this problem, we propose a novel strategy called HIerarchical GrapH Tokenization (HIGHT). HIGHT employs a hierarchical graph tokenizer that extracts and encodes the hierarchy of node, motif, and graph levels of informative tokens to improve the graph perception of LLMs. HIGHT also adopts an augmented graph-language supervised fine-tuning dataset, enriched with the hierarchical graph information, to further enhance the graph-language alignment. Extensive experiments on 7 molecule-centric benchmarks confirm the effectiveness of HIGHT in reducing hallucination by 40%, as well as significant improvements in various molecule-language downstream tasks.

Related papers

• A Hierarchical Language Model For Interpretable Graph Reasoning [47.460255447561906]
  We introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, and robustness, while reducing computational costs on large-scale graph tasks. Comprehensive evaluations across diverse graph reasoning and real-world tasks of node, link, and graph-levels highlight the superiority of our method.
  arXiv  Detail & Related papers  (2024-10-29T00:28:02Z)
• Graph Linearization Methods for Reasoning on Graphs with Large Language Models [25.3545522174459]
  Graphs should be linearized to reflect certain properties of natural language text, such as local dependency and global alignment. We develop several graph linearization methods based on graph centrality, degeneracy, and node relabeling schemes. Our work introduces novel graph representations suitable for LLMs, contributing to the potential integration of graph machine learning with the trend of multi-modal processing.
  arXiv  Detail & Related papers  (2024-10-25T11:51:37Z)
• Dynamic and Textual Graph Generation Via Large-Scale LLM-based Agent Simulation [70.60461609393779]
  GraphAgent-Generator (GAG) is a novel simulation-based framework for dynamic graph generation. Our framework effectively replicates seven macro-level structural characteristics in established network science theories. It supports generating graphs with up to nearly 100,000 nodes or 10 million edges, with a minimum speed-up of 90.4%.
  arXiv  Detail & Related papers  (2024-10-13T12:57:08Z)
• GraphEdit: Large Language Models for Graph Structure Learning [62.618818029177355]
  Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data. Existing GSL methods heavily depend on explicit graph structural information as supervision signals. We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
  arXiv  Detail & Related papers  (2024-02-23T08:29:42Z)
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [61.93058781222079]
  We develop a flexible question-answering framework targeting real-world textual graphs. We introduce the first retrieval-augmented generation (RAG) approach for general textual graphs. G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem.
  arXiv  Detail & Related papers  (2024-02-12T13:13:04Z)
• GraphGPT: Graph Instruction Tuning for Large Language Models [27.036935149004726]
  Graph Neural Networks (GNNs) have evolved to understand graph structures. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Our research tackles this by advancing graph model generalization in zero-shot learning environments.
  arXiv  Detail & Related papers  (2023-10-19T06:17:46Z)
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data [91.27527985415007]
  Existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph. We advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set.
  arXiv  Detail & Related papers  (2023-06-05T07:53:52Z)
• GraphMAE: Self-Supervised Masked Graph Autoencoders [52.06140191214428]
  We present a masked graph autoencoder GraphMAE that mitigates issues for generative self-supervised graph learning. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE--a simple graph autoencoder with our careful designs--can consistently generate outperformance over both contrastive and generative state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-05-22T11:57:08Z)
• Multi-Level Graph Contrastive Learning [38.022118893733804]
  We propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs. The original graph is first-order approximation structure and contains uncertainty or error, while the $k$NN graph generated by encoding features preserves high-order proximity. Extensive experiments indicate MLGCL achieves promising results compared with the existing state-of-the-art graph representation learning methods on seven datasets.
  arXiv  Detail & Related papers  (2021-07-06T14:24:43Z)
• Hierarchical Inter-Message Passing for Learning on Molecular Graphs [9.478108870211365]
  We present a hierarchical neural message passing architecture for learning on molecular graphs. Our method is able to overcome some of the restrictions known from classical GNNs, like detecting cycles, while still being very efficient to train.
  arXiv  Detail & Related papers  (2020-06-22T12:25:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.