Pith. sign in

REVIEW 7 cited by

Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.14324 v3 pith:SDPR5HK6 submitted 2023-11-24 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords llmsgraphtopologicaledgelanguagenodeworkenhance
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The latest advancements in large language models (LLMs) have revolutionized the field of natural language processing (NLP). Inspired by the success of LLMs in NLP tasks, some recent work has begun investigating the potential of applying LLMs in graph learning tasks. However, most of the existing work focuses on utilizing LLMs as powerful node feature augmenters, leaving employing LLMs to enhance graph topological structures an understudied problem. In this work, we explore how to leverage the information retrieval and text generation capabilities of LLMs to refine/enhance the topological structure of text-attributed graphs (TAGs) under the node classification setting. First, we propose using LLMs to help remove unreliable edges and add reliable ones in the TAG. Specifically, we first let the LLM output the semantic similarity between node attributes through delicate prompt designs, and then perform edge deletion and edge addition based on the similarity. Second, we propose using pseudo-labels generated by the LLM to improve graph topology, that is, we introduce the pseudo-label propagation as a regularization to guide the graph neural network (GNN) in learning proper edge weights. Finally, we incorporate the two aforementioned LLM-based methods for graph topological refinement into the process of GNN training, and perform extensive experiments on four real-world datasets. The experimental results demonstrate the effectiveness of LLM-based graph topology refinement (achieving a 0.15%--2.47% performance gain on public benchmarks).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data

    cs.AI 2025-05 conditional novelty 7.0 of 10

    Fine-tuning LLMs on graph tasks with a restricted attention window that includes partial graph links, then switching to a fully connected window at inference, improves node classification over standard full-attention ...

  2. Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment

    cs.LG 2025-06 conditional novelty 6.0 of 10

    GAGA matches or exceeds state-of-the-art accuracy on several text-attributed graph benchmarks while requiring large language model annotations for only 1% of nodes or edges.

  3. An Automatic Graph Construction Framework based on Large Language Models for Recommendation

    cs.IR 2024-12 conditional novelty 6.0 of 10

    AutoGraph uses LLM semantic vectors, residual vector quantization, and metapath GAT propagation to construct an automatic graph that improves recommendation across four backbones and three datasets.

  4. GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation

    cs.AI 2025-01 conditional novelty 5.0 of 10

    A dual-graph RGCN combined with 3D conditional diffusion reaches 58.9% unknown-class and 67.6% known-class top-1 retrosynthesis accuracy on USPTO-50k, beating prior semi-template methods.

  5. Hyperbolic Contrastive Learning with Model-augmentation for Knowledge-aware Recommendation

    cs.IR 2025-05 conditional novelty 4.0 of 10

    A knowledge-aware recommender combining Lorentz-model hyperbolic embeddings with three model-level contrastive augmentations reports up to 11.03% improvement over the strongest baseline.

  6. Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning

    cs.LG 2025-01 conditional novelty 4.0 of 10

    LLM-for-graph methods are divided into Graph2text and Graph2token paradigms, with four conversion challenges and a model-selection guideline.

  7. Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017

    cs.CR 2025-06 reject novelty 3.0 of 10

    A benchmark finds supervised MLP and CNN detect known attacks almost perfectly but miss most novel attacks, while OCSVM generalizes better to unseen threats.

Pith tools