Pith. sign in

REVIEW 5 cited by

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2408.14512 v3 pith:DRR5WSH7 submitted 2024-08-25 cs.LG cs.AIcs.CL

Duo Wang , Yuan Zuo , Fengzhi Li , Junjie Wu This is my paper
classification cs.LGcs.AIcs.CL
keywords graphzero-shotlearningtokenembeddingsllmsmethodsrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN's representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method's effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Attacking Graph Foundation Models Through Their Shared Representation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A shared representation layer in graph foundation models is a distinct attack surface: input edits break three of six models and one spectral tokenizer is uniquely fragile.

  2. KoRe: Compact Knowledge Representations for Large Language Models

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    KoRe encodes 1-hop knowledge graph subgraphs as compact discrete tokens for injection into LLMs, achieving competitive benchmark performance with up to 10x token reduction.

  3. A Comprehensive Data-centric Overview of Federated Graph Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A data-centric taxonomy for Federated Graph Learning that classifies 79 studies by data characteristics and data utilization, plus a discussion of integration with pre-trained large models.

  4. TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks

    cs.LG 2025-06 conditional novelty 5.0 of 10

    GraphLLMs are broadly vulnerable to text, graph structure, and prompt label attacks, but the severity depends heavily on the model and dataset.

  5. ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

    cs.CL 2025-10 conditional novelty 4.0 of 10

    Using residual quantization to represent KG entities as code tokens lets an LLM do link prediction and reach reported state-of-the-art MRR on WN18RR (0.608) and FB15k-237 (0.467) when ontology constraints are added.

Pith tools