paper-with-me

Papers

Aligning Transformers with Weisfeiler-Leman

2024-06-05 · Luis Müller, Christopher Morris

Graph neural network architectures aligned with the $k$-dimensional Weisfeiler--Leman ($k$-WL) hierarchy offer theoretically well-understood expressive power. However, these architectures often fail to deliver state-of-the-art predictive performance on real-world graphs, limiting their practical utility. While recent works aligning graph transformer architectures with the $k$-WL hierarchy have shown promising empirical results, employing transformers for higher orders of $k$ remains challenging due to a prohibitive runtime and memory complexity of self-attention as well as impractical architectural assumptions, such as an infeasible number of attention heads. Here, we advance the alignment of transformers with the $k$-WL hierarchy, showing stronger expressivity results for each $k$, making them more feasible in practice. In addition, we develop a theoretical framework that allows the study of established positional encodings such as Laplacian PEs and SPE. We evaluate our transformers on the large-scale PCQM4Mv2 dataset, showing competitive predictive performance with the state-of-the-art and demonstrating strong downstream performance when fine-tuning them on small-scale molecular datasets. Our code is available at https://github.com/luis-mueller/wl-transformers.

📄 PDF Abstract BibTeX arXiv:2406.03148

Code (1)

luis-mueller/wl-transformers 공식 구현 pytorch

Tasks

Graph Neural Network

Methods 이 논문이 사용한 방법론

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 $x$…
LapEigen 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Laplacian PE Laplacian eigenvectors represent a natural generalization of the…
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…
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

Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited

2022-05-22 · Nils M. Kriege

Random walk kernels have been introduced in seminal work on graph learning and were later largely superseded by kernels based on the Weisfeiler-Leman test for graph isomorphism. We give a unified view on both classes of …

Graph Learning

Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization

2025-08-14 · Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto, Magdalena Ortiz 외 arxiv

We present a novel approach for graph classification based on tabularizing graph data via new variants of the Weisfeiler-Leman algorithm and then applying methods for tabular data. The variants are obtained by modifying …

Graph ClassificationGraph Learning

Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing

2021-02-17 · Jan Tönshoff, Martin Ritzert, Hinrikus Wolf, Martin Grohe

We propose CRaWl, a novel neural network architecture for graph learning. Like graph neural networks, CRaWl layers update node features on a graph and thus can freely be combined or interleaved with GNN layers. Yet CRaWl…

Graph ClassificationGraph LearningGraph Regressionregression

Weisfeiler and Leman Go Relational

2022-11-30 · Pablo Barcelo, Mikhail Galkin, Christopher Morris, Miguel Romero Orth

Knowledge graphs, modeling multi-relational data, improve numerous applications such as question answering or graph logical reasoning. Many graph neural networks for such data emerged recently, often outperforming shallo…

Knowledge GraphsLogical ReasoningQuestion Answering

The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs

2021-05-12 · Christopher Morris, Matthias Fey, Nils M. Kriege

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for (supervised) machine learning with gr…

BIG-bench Machine LearningNode Classification