English
Related papers

Related papers: Homomorphism Counts as Structural Encodings for Gr…

200 papers

Graph transformers extend global self-attention to graph-structured data, achieving notable success in graph learning. Recently, random walk structural encoding (RWSE) has been found to further enhance their predictive power by encoding…

Machine Learning · Computer Science 2025-06-03 Louis Airale , Antonio Longa , Mattia Rigon , Andrea Passerini , Roberto Passerone

Graph neural networks (GNNs) have become the standard learning architectures for graphs. GNNs have been applied to numerous domains ranging from quantum chemistry, recommender systems to knowledge graphs and natural language processing. A…

Machine Learning · Computer Science 2022-02-11 Vijay Prakash Dwivedi , Anh Tuan Luu , Thomas Laurent , Yoshua Bengio , Xavier Bresson

While graph neural networks (GNNs) have achieved great success in learning from graph-structured data, their reliance on local, pairwise message passing restricts their ability to capture complex, high-order subgraph patterns. leading to…

Machine Learning · Computer Science 2025-09-12 Junda Ye , Zhongbao Zhang , Li Sun , Siqiang Luo

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

Transformers were originally proposed as a sequence-to-sequence model for text but have become vital for a wide range of modalities, including images, audio, video, and undirected graphs. However, transformers for directed graphs are a…

Machine Learning · Computer Science 2023-09-01 Simon Geisler , Yujia Li , Daniel Mankowitz , Ali Taylan Cemgil , Stephan Günnemann , Cosmin Paduraru

Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been…

Machine Learning · Computer Science 2026-03-16 Yinan Huang , Haoyu Wang , Pan Li

Recent advancements in large-scale pre-training have shown the potential to learn generalizable representations for downstream tasks. In the graph domain, however, capturing and transferring structural information across different graph…

Machine Learning · Computer Science 2026-02-24 Jialin Chen , Haolan Zuo , Haoyu Peter Wang , Siqi Miao , Pan Li , Rex Ying

The most prevalent class of neural networks operating on graphs are message passing neural networks (MPNNs), in which the representation of a node is updated iteratively by aggregating information in the 1-hop neighborhood. Since this…

Machine Learning · Computer Science 2023-10-25 Floor Eijkelboom , Erik Bekkers , Michael Bronstein , Francesco Di Giovanni

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

Designing effective positional encodings for graphs is key to building powerful graph transformers and enhancing message-passing graph neural networks. Although widespread, using Laplacian eigenvectors as positional encodings faces two…

Machine Learning · Computer Science 2024-06-11 Yinan Huang , William Lu , Joshua Robinson , Yu Yang , Muhan Zhang , Stefanie Jegelka , Pan Li

Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced their performance across various graph learning tasks. However, the general applicability of these…

Machine Learning · Computer Science 2025-03-04 Billy Joe Franks , Moshe Eliasof , Semih Cantürk , Guy Wolf , Carola-Bibiane Schönlieb , Sophie Fellenz , Marius Kloft

Graph homomorphism counts, first explored by Lov\'asz in 1967, have recently garnered interest as a powerful tool in graph-based machine learning. Grohe (PODS 2020) proposed the theoretical foundations for using homomorphism counts in…

Machine Learning · Computer Science 2023-11-21 Hinrikus Wolf , Luca Oeljeklaus , Pascal Kühner , Martin Grohe

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…

A large driver of the complexity of graph learning is the interplay between structure and features. When analyzing the expressivity of graph neural networks, however, existing approaches ignore features in favor of structure, making it…

Machine Learning · Computer Science 2026-03-04 Martin Carrasco , Olga Zaghen , Kavir Sumaraj , Erik Bekkers , Bastian Rieck

In this paper, we study the graph classification problem from the graph homomorphism perspective. We consider the homomorphisms from $F$ to $G$, where $G$ is a graph of interest (e.g. molecules or social networks) and $F$ belongs to some…

Machine Learning · Computer Science 2020-07-03 Hoang NT , Takanori Maehara

Cycles are fundamental elements in graph-structured data and have demonstrated their effectiveness in enhancing graph learning models. To encode such information into a graph learning framework, prior works often extract a summary quantity,…

Machine Learning · Computer Science 2023-12-01 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Chao Chen , Yusu Wang

Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural networks (MPNNs) face well-documented theoretical and…

Machine Learning · Computer Science 2026-05-15 Juan Amboage , Ernst Röell , Patrick Schnider , Bastian Rieck

We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find…

Message-passing has proved to be an effective way to design graph neural networks, as it is able to leverage both permutation equivariance and an inductive bias towards learning local structures in order to achieve good generalization.…

Machine Learning · Computer Science 2020-10-26 Clement Vignac , Andreas Loukas , Pascal Frossard

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared…

Machine Learning · Computer Science 2021-11-25 Chengxuan Ying , Tianle Cai , Shengjie Luo , Shuxin Zheng , Guolin Ke , Di He , Yanming Shen , Tie-Yan Liu
‹ Prev 1 2 3 10 Next ›