English
Related papers

Related papers: Rewiring with Positional Encodings for Graph Neura…

200 papers

Majority of the existing graph neural networks (GNN) learn node embeddings that encode their local neighborhoods but not their positions. Consequently, two nodes that are vastly distant but located in similar local neighborhoods map to…

Social and Information Networks · Computer Science 2021-08-23 Sunil Nishad , Shubhangi Agarwal , Arnab Bhattacharya , Sayan Ranu

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the…

Machine Learning · Computer Science 2019-06-17 Jiaxuan You , Rex Ying , Jure Leskovec

Two main families of node feature augmentation schemes have been explored for enhancing GNNs: random features and spectral positional encoding. Surprisingly, however, there is still no clear understanding of the relation between these two…

Machine Learning · Computer Science 2023-07-20 Moshe Eliasof , Fabrizio Frasca , Beatrice Bevilacqua , Eran Treister , Gal Chechik , Haggai Maron

Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shape representations, and beyond. Most INR methods are based on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Guillaume Perez , Janarbek Matai , Takahiro Harada

In this work, we propose novel families of positional encodings tailored to graph neural networks obtained with quantum computers. These encodings leverage the long-range correlations inherent in quantum systems that arise from mapping the…

Most Graph Neural Networks (GNNs) cannot distinguish some graphs or indeed some pairs of nodes within a graph. This makes it impossible to solve certain classification tasks. However, adding additional node features to these models can…

Machine Learning · Computer Science 2022-09-20 Beni Egressy , Roger Wattenhofer

Recently a variety of methods have been developed to encode graphs into low-dimensional vectors that can be easily exploited by machine learning algorithms. The majority of these methods start by embedding the graph nodes into a…

Machine Learning · Computer Science 2018-09-13 Yu Jin , Joseph F. JaJa

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

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

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the…

Machine Learning · Computer Science 2024-11-05 Zhenyue Qin , Yiqun Zhang Saeed Anwar , Dongwoo Kim , Yang Liu , Pan Ji , Tom Gedeon

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

Graph Neural Networks (GNNs) bring the power of deep representation learning to graph and relational data and achieve state-of-the-art performance in many applications. GNNs compute node representations by taking into account the topology…

Machine Learning · Computer Science 2021-09-10 Maria Kalantzi , George Karypis

Positional Encodings (PEs) are essential for injecting structural information into Graph Neural Networks (GNNs), particularly Graph Transformers, yet their empirical impact remains insufficiently understood. We introduce a unified…

Machine Learning · Computer Science 2026-01-15 Florian Grötschla , Jiaqing Xie , Roger Wattenhofer

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which…

Machine Learning · Computer Science 2019-10-01 Yao Ma , Suhang Wang , Tyler Derr , Lingfei Wu , Jiliang Tang

Graph Neural Networks (GNNs) have emerged as promising solutions for collaborative filtering (CF) through the modeling of user-item interaction graphs. The nucleus of existing GNN-based recommender systems involves recursive message passing…

Machine Learning · Computer Science 2024-05-21 Peiyan Zhang , Yuchen Yan , Xi Zhang , Chaozhuo Li , Senzhang Wang , Feiran Huang , Sunghun Kim

Positional Encoder Graph Neural Networks (PE-GNNs) are among the most effective models for learning from continuous spatial data. However, their predictive distributions are often poorly calibrated, limiting their utility in applications…

This research aims to improve the accuracy of complex volleyball predictions and provide more meaningful insights to coaches and players. We introduce a specialized graph encoding technique to add additional contact-by-contact volleyball…

Machine Learning · Computer Science 2023-08-23 Rhys Tracy , Haotian Xia , Alex Rasla , Yuan-Fang Wang , Ambuj Singh

In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers. In this paper, we propose an architecture that integrates both approaches, dubbed Subgraphormer,…

Machine Learning · Computer Science 2024-05-29 Guy Bar-Shalom , Beatrice Bevilacqua , Haggai Maron

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

The local inductive bias of message-passing graph neural networks (GNNs) hampers their ability to exploit key structural information (e.g., connectivity and cycles). Positional encoding (PE) and Persistent Homology (PH) have emerged as two…

Machine Learning · Computer Science 2025-06-09 Yogesh Verma , Amauri H. Souza , Vikas Garg