English
Related papers

Related papers: Aligning Transformers with Weisfeiler-Leman

200 papers

We show theoretically and empirically that the linear Transformer, when applied to graph data, can implement algorithms that solve canonical problems such as electric flow and eigenvector decomposition. The Transformer has access to…

Machine Learning · Computer Science 2025-03-04 Xiang Cheng , Lawrence Carin , Suvrit Sra

Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby their theoretical expressive power is limited to the…

Machine Learning · Computer Science 2023-09-19 Dingmin Wang , Shengchao Liu , Hanchen Wang , Bernardo Cuenca Grau , Linfeng Song , Jian Tang , Song Le , Qi Liu

Transformers, as the fundamental deep learning architecture, have demonstrated great capability in reasoning. This paper studies the generalizable first-order logical reasoning ability of transformers with their parameterized knowledge and…

Computation and Language · Computer Science 2025-07-11 Tianshi Zheng , Jiazheng Wang , Zihao Wang , Jiaxin Bai , Hang Yin , Zheye Deng , Yangqiu Song , Jianxin Li

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer…

Machine Learning · Computer Science 2025-04-17 Anh Tong , Thanh Nguyen-Tang , Dongeun Lee , Duc Nguyen , Toan Tran , David Hall , Cheongwoong Kang , Jaesik Choi

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Computation and Language · Computer Science 2025-03-31 Zhuo-Yang Song , Zeyu Li , Qing-Hong Cao , Ming-xing Luo , Hua Xing Zhu

Graph Transformers excel in long-range dependency modeling, but generally require quadratic memory complexity in the number of nodes in an input graph, and hence have trouble scaling to large graphs. Sparse attention variants such as…

Machine Learning · Computer Science 2024-11-26 Hamed Shirzad , Honghao Lin , Balaji Venkatachalam , Ameya Velingker , David Woodruff , Danica Sutherland

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

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Machine Learning · Computer Science 2023-03-02 Haiteng Zhao , Shuming Ma , Dongdong Zhang , Zhi-Hong Deng , Furu Wei

The k-nearest neighbors (kNN) algorithm is a cornerstone of non-parametric classification in artificial intelligence, yet its deployment in large-scale applications is persistently constrained by the computational trade-off between…

Machine Learning · Computer Science 2026-01-26 Jiaye Li , Gang Chen , Hang Xu , Shichao Zhang

Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the…

Computation and Language · Computer Science 2024-10-07 Anej Svete , Nadav Borenstein , Mike Zhou , Isabelle Augenstein , Ryan Cotterell

Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the…

Computation and Language · Computer Science 2023-11-22 Zhen Bi , Siyuan Cheng , Jing Chen , Xiaozhuan Liang , Feiyu Xiong , Ningyu Zhang

The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing -- aggregating information from 1-hop neighbors repeatedly. However, the expressive power of 1-hop message passing is bounded by the…

Machine Learning · Computer Science 2023-01-09 Jiarui Feng , Yixin Chen , Fuhai Li , Anindya Sarkar , Muhan Zhang

We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes…

Machine Learning · Computer Science 2022-02-28 Georgios Kollias , Vasileios Kalantzis , Tsuyoshi Idé , Aurélie Lozano , Naoki Abe

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test. We adapt Manifold-Constrained Hyper-Connections (\mhc)~\citep{xie2025mhc}, recently proposed for…

Machine Learning · Computer Science 2026-01-07 Subhankar Mishra

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

Transformer networks have achieved remarkable empirical success across a wide range of applications, yet their theoretical expressive power remains insufficiently understood. In this paper, we study the expressive capabilities of…

Machine Learning · Computer Science 2026-03-04 Linyan Gu , Lihua Yang , Feng Zhou

Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance in various visual…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Yuxin Fang , Xinggang Wang , Rui Wu , Wenyu Liu

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility…

Machine Learning · Computer Science 2025-12-23 Ahsan Shehzad , Feng Xia , Shagufta Abid , Ciyuan Peng , Shuo Yu , Dongyu Zhang , Karin Verspoor

From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with…

Machine Learning · Computer Science 2020-12-03 Lei Chen , Zhengdao Chen , Joan Bruna