Efficient Tuning and Inference for Large Language Models on Textual Graphs

• URL: http://arxiv.org/abs/2401.15569v2
• Date: Wed, 24 Jul 2024 08:56:11 GMT
• Title: Efficient Tuning and Inference for Large Language Models on Textual Graphs
• Authors: Yun Zhu, Yaoke Wang, Haizhou Shi, Siliang Tang,
• Abstract summary: ENGINE is a parameter- and memory-efficient fine-tuning method for textual graphs with an LLM encoder. Experiments on textual graphs demonstrate our method's effectiveness by achieving the best model performance. We introduce two variants with caching and dynamic early exit to further enhance training and inference speed.
• Score: 29.54120519469645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder and a subsequent graph neural network (GNN) to solve this problem. In light of recent advancements in large language models (LLMs), it is apparent that integrating LLMs for enhanced textual encoding can substantially improve the performance of textual graphs. Nevertheless, the efficiency of these methods poses a significant challenge. In this paper, we propose ENGINE, a parameter- and memory-efficient fine-tuning method for textual graphs with an LLM encoder. The key insight is to combine the LLMs and GNNs through a tunable side structure, which significantly reduces the training complexity without impairing the joint model's capacity. Extensive experiments on textual graphs demonstrate our method's effectiveness by achieving the best model performance, meanwhile having the lowest training cost compared to previous methods. Moreover, we introduce two variants with caching and dynamic early exit to further enhance training and inference speed. Specifically, caching accelerates ENGINE's training by 12x, and dynamic early exit achieves up to 5x faster inference with a negligible performance drop (at maximum 1.17% relevant drop across 7 datasets). Our codes are available at: https://github.com/ZhuYun97/ENGINE

Related papers

• Gradient Transformation: Towards Efficient and Model-Agnostic Unlearning for Dynamic Graph Neural Networks [66.70786325911124]
  Graph unlearning has emerged as an essential tool for safeguarding user privacy and mitigating the negative impacts of undesirable data. With the increasing prevalence of DGNNs, it becomes imperative to investigate the implementation of dynamic graph unlearning. We propose an effective, efficient, model-agnostic, and post-processing method to implement DGNN unlearning.
  arXiv  Detail & Related papers  (2024-05-23T10:26:18Z)
• Parameter-Efficient Tuning Large Language Models for Graph Representation Learning [62.26278815157628]
  We introduce Graph-aware. Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning. We use a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt. We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations.
  arXiv  Detail & Related papers  (2024-04-28T18:36:59Z)
• GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism [10.573861741540853]
  We propose a graph-guided self-attention mechanism, GraSAME, for pretrained language models. GraSAME seamlessly incorporates token-level structural information into PLMs without necessitating additional alignment or concatenation efforts. Our experiments on the graph-to-text generation task demonstrate that GraSAME outperforms baseline models and achieves results comparable to state-of-the-art (SOTA) models on WebNLG datasets.
  arXiv  Detail & Related papers  (2024-04-10T11:03:57Z)
• Efficient Large Language Models Fine-Tuning On Graphs [23.19795835873144]
  Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications. We introduce a novel and efficient approach for the end-to-end fine-tuning of Large Language Models (LLMs) on TAGs, named LEADING.
  arXiv  Detail & Related papers  (2023-12-07T22:35:16Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning [51.90524745663737]
  A key innovation is our use of explanations as features, which can be used to boost GNN performance on downstream tasks. Our method achieves state-of-the-art results on well-established TAG datasets. Our method significantly speeds up training, achieving a 2.88 times improvement over the closest baseline on ogbn-arxiv.
  arXiv  Detail & Related papers  (2023-05-31T03:18:03Z)
• Learning on Large-scale Text-attributed Graphs via Variational Inference [44.558681850874336]
  This paper studies learning on text-attributed graphs (TAGs), where each node is associated with a text description. We propose an efficient and effective solution to learning on large text-attributed graphs by fusing graph structure and language learning with a variational Expectation-Maximization framework.
  arXiv  Detail & Related papers  (2022-10-26T13:40:57Z)
• GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph [53.70520466556453]
  We propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow. In addition, a progressive learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph.
  arXiv  Detail & Related papers  (2021-05-06T12:20:41Z)
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking [58.30147362745852]
  Data association across frames is at the core of Multiple Object Tracking (MOT) task. Existing methods mostly ignore the context information among tracklets and intra-frame detections. We propose a novel learnable graph matching method to address these issues.
  arXiv  Detail & Related papers  (2021-03-30T08:58:45Z)

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.