paper-with-me

Papers

Plain Transformers Can be Powerful Graph Learners

2025-04-17 · Liheng Ma, Soumyasundar Pal, Yingxue Zhang, Philip H. S. Torr, Mark Coates

Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have attempted to migrate Transformers to graph learning, but most advanced Graph Transformers (GTs) have strayed far from plain Transformers, exhibiting major architectural differences either by integrating message-passing or incorporating sophisticated attention mechanisms. These divergences hinder the easy adoption of training advances for Transformers developed in other domains. Contrary to previous GTs, this work demonstrates that the plain Transformer architecture can be a powerful graph learner. To achieve this, we propose to incorporate three simple, minimal, and easy-to-implement modifications to the plain Transformer architecture to construct our Powerful Plain Graph Transformers (PPGT): (1) simplified $L_2$ attention for measuring the magnitude closeness among tokens; (2) adaptive root-mean-square normalization to preserve token magnitude information; and (3) a simple MLP-based stem for graph positional encoding. Consistent with its theoretical expressivity, PPGT demonstrates noteworthy realized expressivity on the empirical graph expressivity benchmark, comparing favorably to more complicated competitors such as subgraph GNNs and higher-order GNNs. Its outstanding empirical performance across various graph datasets also justifies the practical effectiveness of PPGT.

📄 PDF Abstract BibTeX arXiv:2504.12588

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation

2022-10-20 · Tien-Cuong Bui, Van-Duc Le, Wen-Syan Li, Sang Kyun Cha

Graph Neural Networks (GNNs) have become increasingly ubiquitous in numerous applications and systems, necessitating explanations of their predictions, especially when making critical decisions. However, explaining GNNs …

Knowledge Distillation

Pure Transformers are Powerful Graph Learners

2022-07-06 · Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min, Sungjun Cho 외

We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent token…

Graph ClassificationGraph LearningGraph RegressionInductive Bias+1

CaTs and DAGs: Integrating Directed Acyclic Graphs with Transformers and Fully-Connected Neural Networks for Causally Constrained Predictions

2024-10-18 · Matthew J. Vowels, Mathieu Rochat, Sina Akbari

Artificial Neural Networks (ANNs), including fully-connected networks and transformers, are highly flexible and powerful function approximators, widely applied in fields like computer vision and natural language processi…

When BERT Fails -- The Limits of EHR Classification

2022-07-26 · Augusto Garcia-Agundez, Carsten Eickhoff

Transformers are powerful text representation learners, useful for all kinds of clinical decision support tasks. Although they outperform baselines on readmission prediction, they are not infallible. Here, we look into o…

ClassificationReadmission Prediction

Plain Transformers are Surprisingly Powerful Link Predictors

2026-02-02 · Quang Truong, Yu Song, Donald Loveland, Mingxuan Ju 외 arxiv

Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipel…

Link Prediction