English
Related papers

Related papers: Graph Inductive Biases in Transformers without Mes…

200 papers

The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the…

Machine Learning · Computer Science 2020-02-13 Komal K. Teru , Etienne Denis , William L. Hamilton

Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power.…

Machine Learning · Computer Science 2024-05-07 Wenhao Zhu , Guojie Song , Liang Wang , Shaoguo Liu

Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property prediction and brain connectome analysis. Importantly, recent works…

Machine Learning · Computer Science 2022-04-04 Kamilia Mullakaeva , Luca Cosmo , Anees Kazi , Seyed-Ahmad Ahmadi , Nassir Navab , Michael M. Bronstein

Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learning tasks poses statistical and computational challenges. In…

Machine Learning · Statistics 2019-05-16 Aditya Grover , Aaron Zweig , Stefano Ermon

We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization. Our experiments show that our graph network models, which implement…

Machine Learning · Computer Science 2019-11-04 Miles D. Cranmer , Rui Xu , Peter Battaglia , Shirley Ho

The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons. Unlike graph neural networks that restrict…

Computation and Language · Computer Science 2019-12-03 Deng Cai , Wai Lam

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or…

Machine Learning · Statistics 2018-02-06 Petar Veličković , Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Liò , Yoshua Bengio

Learning embeddings from large-scale networks is an open challenge. Despite the overwhelming number of existing methods, is is unclear how to exploit network structure in a way that generalizes easily to unseen nodes, edges or graphs. In…

Machine Learning · Computer Science 2020-09-29 Nurudin Alvarez-Gonzalez , Andreas Kaltenbrunner , Vicenç Gómez

A current goal in the graph neural network literature is to enable transformers to operate on graph-structured data, given their success on language and vision tasks. Since the transformer's original sinusoidal positional encodings (PEs)…

Machine Learning · Computer Science 2023-04-11 Patrick Soga , David Chiang

Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in particular…

Computation and Language · Computer Science 2026-05-18 Tianyu Huang , Yida Zhao , Chuyan Zhou , Kewei Tu

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Chenhao Xu , Chang-Tsun Li , Chee Peng Lim , Douglas Creighton

In the field of graph signal processing (GSP), directed graphs present a particular challenge for the "standard approaches" of GSP to due to their asymmetric nature. The presence of negative- or complex-weight directed edges, a graphical…

Signal Processing · Electrical Eng. & Systems 2020-03-03 Kevin Schultz , Marisel Villafane-Delgado

Inspired by the success of foundation models in applications such as ChatGPT, as graph data has been ubiquitous, one can envision the far-reaching impacts that can be brought by Graph Foundation Models (GFMs) with broader applications in…

Machine Learning · Computer Science 2024-11-12 Zehong Wang , Zheyuan Zhang , Nitesh V Chawla , Chuxu Zhang , Yanfang Ye

Graph neural networks (GNNs) have garnered significant attention due to their ability to represent graph data. Among various GNN variants, graph attention network (GAT) stands out since it is able to dynamically learn the importance of…

Machine Learning · Computer Science 2024-08-19 Tiqiao Wei , Ye Yuan

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing…

The dominant graph neural networks (GNNs) over-rely on the graph links, several serious performance problems with which have been witnessed already, e.g., suspended animation problem and over-smoothing problem. What's more, the inherently…

Machine Learning · Computer Science 2020-01-23 Jiawei Zhang , Haopeng Zhang , Congying Xia , Li Sun

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Machine Learning · Computer Science 2024-09-11 Minhong Zhu , Zhenhao Zhao , Weiran Cai

Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics. However, the increasingly heterogeneous graph datasets call…

Machine Learning · Computer Science 2023-01-25 Yasha Ektefaie , George Dasoulas , Ayush Noori , Maha Farhat , Marinka Zitnik

Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes…

Machine Learning · Computer Science 2025-11-07 Yufei He , Zhenyu Hou , Yukuo Cen , Jun Hu , Feng He , Xu Cheng , Jie Tang , Bryan Hooi

Graph Transformers typically rely on explicit positional or structural encodings and dense global attention to incorporate graph topology. In this work, we show that neither is essential. We introduce HopFormer, a graph Transformer that…

Machine Learning · Computer Science 2026-02-03 Sanggeon Yun , Raheeb Hassan , Ryozo Masukawa , Sungheon Jeong , Mohsen Imani