paper-with-me

Papers

Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification

2024-12-19 · Zijie Zhou, Zhaoqi Lu, Xuekai Wei, Rongqin Chen, Shenghui Zhang, Pak Lon Ip, Leong Hou U

Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and over-squashing limit the receptive field in message passing processes. Graph Transformers were introduced to address these issues, achieving a global receptive field but suffering from the noise of irrelevant nodes and loss of structural information. Therefore, drawing inspiration from fine-grained token-based representation learning in Natural Language Processing (NLP), we propose the Structure-aware Multi-token Graph Transformer (Tokenphormer), which generates multiple tokens to effectively capture local and structural information and explore global information at different levels of granularity. Specifically, we first introduce the walk-token generated by mixed walks consisting of four walk types to explore the graph and capture structure and contextual information flexibly. To ensure local and global information coverage, we also introduce the SGPM-token (obtained through the Self-supervised Graph Pre-train Model, SGPM) and the hop-token, extending the length and density limit of the walk-token, respectively. Finally, these expressive tokens are fed into the Transformer model to learn node representations collaboratively. Experimental results demonstrate that the capability of the proposed Tokenphormer can achieve state-of-the-art performance on node classification tasks.

📄 PDF Abstract BibTeX arXiv:2412.15302

Code (1)

Dodo-D-Caster/Tokenphormer 공식 구현 pytorch

Tasks

Node ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
LapEigen 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning

2026-06-10 · Zhirui Chen, Ziwei Chen, Ling Shao arxiv

Multi-modal large language models (MLLMs) depend on in-context learning (ICL) for rapid task adaptation, but their scalability is severely limited by finite context windows and the growing cost of key-value (KV) caches i…

Graph Matching

A Structure-Aware Argument Encoder for Literature Discourse Analysis

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context. In this paper, we propose to separate tokens int…

PositionRepresentation LearningSentence

When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models

2026-06-02 · Ding Zhang, Runtao Zhou, Wenqing Zheng, Rizal Fathony 외 arxiv

Graph Language Models (GLMs) have become a promising direction for adapting Large Language Models (LLMs) to graph learning tasks. By transforming graph topology and node information into graph tokens, GLMs allow LLMs to …

Graph Learning

A Structure-Aware Argument Encoder for Literature Discourse Analysis

2022-10-01 · COLING 2022 10 · Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang 외

Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context. In this paper, we propose to separate tokens int…

PositionRepresentation LearningSentence

<SOG_k>: One LLM Token for Explicit Graph Structural Understanding

2026-02-02 · Jingyao Wu, Bin Lu, Zijun Di, Xiaoying Gan 외 arxiv

Large language models show great potential in unstructured data understanding, but still face significant challenges with graphs due to their structural hallucination. Existing approaches mainly either verbalize graphs i…