English
Related papers

Related papers: LEAP: Local ECT-Based Learnable Positional Encodin…

200 papers

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability.…

Machine Learning · Computer Science 2025-06-17 Yang Liu , Deyu Bo , Wenxuan Cao , Yuan Fang , Yawen Li , Chuan Shi

Graph neural networks (GNNs) are the primary tool for processing graph-structured data. Unfortunately, the most commonly used GNNs, called Message Passing Neural Networks (MPNNs) suffer from several fundamental limitations. To overcome…

Machine Learning · Computer Science 2022-11-11 Sohir Maskey , Ali Parviz , Maximilian Thiessen , Hannes Stärk , Ylli Sadikaj , Haggai Maron

We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs). Our…

Machine Learning · Computer Science 2021-06-11 Grégoire Mialon , Dexiong Chen , Margot Selosse , Julien Mairal

Accurate predictions rely on the expressiveness power of graph deep learning frameworks like graph neural networks and graph transformers, where a positional encoding mechanism has become much more indispensable in recent state-of-the-art…

Machine Learning · Computer Science 2025-06-12 Katherine Tieu , Dongqi Fu , Zihao Li , Ross Maciejewski , Jingrui He

Several recent works use positional encodings to extend the receptive fields of graph neural network (GNN) layers equipped with attention mechanisms. These techniques, however, extend receptive fields to the complete graph, at substantial…

Machine Learning · Computer Science 2023-12-14 Rickard Brüel-Gabrielsson , Mikhail Yurochkin , Justin Solomon

Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood.…

Machine Learning · Computer Science 2024-05-09 Yongze Wang , Haimin Zhang , Qiang Wu , Min Xu

Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these…

Machine Learning · Computer Science 2023-04-12 Weitao Du , Yuanqi Du , Limei Wang , Dieqiao Feng , Guifeng Wang , Shuiwang Ji , Carla Gomes , Zhi-Ming Ma

Graph is a fundamental data structure to model interconnections between entities. Set, on the contrary, stores independent elements. To learn graph representations, current Graph Neural Networks (GNNs) primarily use message passing to…

Machine Learning · Computer Science 2024-06-03 Xiyuan Wang , Pan Li , Muhan Zhang

Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily -- neighboring nodes having similar features and labels--, and therefore…

Machine Learning · Computer Science 2021-10-26 Liheng Ma , Reihaneh Rabbany , Adriana Romero-Soriano

Traditional Graph Self-Supervised Learning (GSSL) struggles to capture complex structural properties well. This limitation stems from two main factors: (1) the inadequacy of conventional Graph Neural Networks (GNNs) in representing…

Machine Learning · Computer Science 2025-02-25 Asiri Wijesinghe , Hao Zhu , Piotr Koniusz

Recently, Transformers for graph representation learning have become increasingly popular, achieving state-of-the-art performance on a wide-variety of graph datasets, either alone or in combination with message-passing graph neural networks…

Machine Learning · Computer Science 2024-05-07 Ayush Garg

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or…

Machine Learning · Computer Science 2025-04-01 Jianqing Liang , Min Chen , Jiye Liang

Early graph prompt tuning approaches relied on task-specific designs for Graph Neural Networks (GNNs), limiting their adaptability across diverse pre-training strategies. In contrast, another promising line of research has investigated…

Machine Learning · Computer Science 2025-12-10 Jinfeng Xu , Zheyu Chen , Shuo Yang , Jinze Li , Hewei Wang , Yijie Li , Edith C. H. Ngai

Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empowering modern GNNs, and in particular graph Transformers. However, designing PSEs that work optimally…

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…

Machine Learning · Computer Science 2023-03-02 Adrián Javaloy , Pablo Sanchez-Martin , Amit Levi , Isabel Valera

We aim to deepen the theoretical understanding of Graph Neural Networks (GNNs) on large graphs, with a focus on their expressive power. Existing analyses relate this notion to the graph isomorphism problem, which is mostly relevant for…

Machine Learning · Computer Science 2023-05-25 Nicolas Keriven , Samuel Vaiter

This overview article makes the case for how topological concepts can enrich research in machine learning. Using the Euler Characteristic Transform (ECT), a geometrical-topological invariant, as a running example, I present different use…

Machine Learning · Computer Science 2026-01-16 Bastian Rieck

Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network…

Machine Learning · Computer Science 2026-05-29 Javier Porras-Valenzuela , Zhiyang Wang , Xiaotao Shang , Yusu Wang , Alejandro Ribeiro

Learning node representations that incorporate information from graph structure benefits wide range of tasks on graph. The majority of existing graph neural networks (GNNs) have limited power in capturing position information for a given…

Machine Learning · Computer Science 2021-06-15 Yuheng Lu , Jinpeng Chen , ChuXiong Sun , Jie Hu

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding:…

Machine Learning · Computer Science 2024-08-26 Mitchell Black , Zhengchao Wan , Gal Mishne , Amir Nayyeri , Yusu Wang