English
Related papers

Related papers: Centered Self-Attention Layers

200 papers

In this work, we generalize the ideas of Kaiming initialization to Graph Neural Networks (GNNs) and propose a new scheme (G-Init) that reduces oversmoothing, leading to very good results in node and graph classification tasks. GNNs are…

Machine Learning · Computer Science 2024-11-01 Dimitrios Kelesis , Dimitris Fotakis , Georgios Paliouras

In this work, we propose to train a graph neural network via resampling from a graphon estimate obtained from the underlying network data. More specifically, the graphon or the link probability matrix of the underlying network is first…

Machine Learning · Computer Science 2021-09-07 Ziqing Hu , Yihao Fang , Lizhen Lin

Graph Neural Networks (GNNs) have emerged as the most powerful weapon for various graph tasks due to the message-passing mechanism's great local information aggregation ability. However, over-smoothing has always hindered GNNs from going…

Machine Learning · Computer Science 2024-03-26 Yundong Sun , Dongjie Zhu , Yansong Wang , Zhaoshuo Tian

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…

Computation and Language · Computer Science 2021-09-15 Mozhdeh Gheini , Xiang Ren , Jonathan May

Oversmoothing is a common phenomenon in a wide range of Graph Neural Networks (GNNs) and Transformers, where performance worsens as the number of layers increases. Instead of characterizing oversmoothing from the view of complete collapse…

Machine Learning · Computer Science 2023-05-03 Xiaojun Guo , Yifei Wang , Tianqi Du , Yisen Wang

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

We propose Scalable Message Passing Neural Networks (SMPNNs) and demonstrate that, by integrating standard convolutional message passing into a Pre-Layer Normalization Transformer-style block instead of attention, we can produce…

Machine Learning · Computer Science 2026-03-11 Haitz Sáez de Ocáriz Borde , Artem Lukoianov , Anastasis Kratsios , Michael Bronstein , Xiaowen Dong

Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms. We herein present a unifying framework for stochastic aggregation…

Machine Learning · Statistics 2021-03-01 Yuanqing Wang , Theofanis Karaletsos

Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space. Existing methods concentrate on learning latent representation via…

Machine Learning · Computer Science 2021-04-28 Zelin Zang , Siyuan Li , Di Wu , Jianzhu Guo , Yongjie Xu , Stan Z. Li

Automatic spelling and grammatical correction systems are one of the most widely used tools within natural language applications. In this thesis, we assume the task of error correction as a type of monolingual machine translation where the…

Computation and Language · Computer Science 2018-10-02 Sina Ahmadi

The development of graph neural networks (GCN) makes it possible to learn structural features from evolving complex networks. Even though a wide range of realistic networks are directed ones, few existing works investigated the properties…

Social and Information Networks · Computer Science 2020-08-25 Jinsong Li , Jianhua Peng , Shuxin Liu , Lintianran Weng , Cong Li

Real-world graphs naturally exhibit hierarchical or cyclical structures that are unfit for the typical Euclidean space. While there exist graph neural networks that leverage hyperbolic or spherical spaces to learn representations that embed…

Machine Learning · Computer Science 2023-09-11 Sungjun Cho , Seunghyuk Cho , Sungwoo Park , Hankook Lee , Honglak Lee , Moontae Lee

The irreducible complexity of natural phenomena has led Graph Neural Networks to be employed as a standard model to perform representation learning tasks on graph-structured data. While their capacity to capture local and global patterns is…

Machine Learning · Computer Science 2024-02-13 Lorenzo Giusti

Transformers use the dense self-attention mechanism which gives a lot of flexibility for long-range connectivity. Over multiple layers of a deep transformer, the number of possible connectivity patterns increases exponentially. However,…

Machine Learning · Computer Science 2023-06-05 Md Shamim Hussain , Mohammed J. Zaki , Dharmashankar Subramanian

End-to-end training of graph neural networks (GNN) on large graphs presents several memory and computational challenges, and limits the application to shallow architectures as depth exponentially increases the memory and space complexities.…

Machine Learning · Computer Science 2023-09-06 Oscar Pina , Verónica Vilaplana

The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models (LLMs). However, a comprehensive mathematical theory that explains its structure and operations…

Machine Learning · Computer Science 2026-04-14 Xue-Cheng Tai , Hao Liu , Lingfeng Li , Raymond H. Chan

Finding the right initialisation for neural networks is crucial to ensure smooth training and good performance. In transformers, the wrong initialisation can lead to one of two failure modes of self-attention layers: rank collapse, where…

Machine Learning · Statistics 2026-05-22 Alessio Giorlandino , Sebastian Goldt

Transformers have recently emerged as powerful neural networks for graph learning, showcasing state-of-the-art performance on several graph property prediction tasks. However, these results have been limited to small-scale graphs, where the…

Machine Learning · Computer Science 2023-12-19 Vijay Prakash Dwivedi , Yozen Liu , Anh Tuan Luu , Xavier Bresson , Neil Shah , Tong Zhao

Over-smoothing and over-squashing have been extensively studied in the literature on Graph Neural Networks (GNNs) over the past years. We challenge this prevailing focus in GNN research, arguing that these phenomena are less critical for…

Machine Learning · Statistics 2026-01-13 Niklas Kormann , Benjamin Doerr , Johannes F. Lutzeyer