English
Related papers

Related papers: Transformers Provably Learn Directed Acyclic Graph…

200 papers

Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges. As a promising decentralized, scalable and secure solution,…

Machine Learning · Computer Science 2025-07-29 Shuaipeng Zhang , Lanju Kong , Yixin Zhang , Wei He , Yongqing Zheng , Han Yu , Lizhen Cui

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

To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server. However, due to the consideration of privacy protection, data owners gradually refuse to share their personalized raw…

Machine Learning · Computer Science 2023-01-18 Erdun Gao , Junjia Chen , Li Shen , Tongliang Liu , Mingming Gong , Howard Bondell

The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision. This…

Machine Learning · Computer Science 2020-02-06 Zhen Peng , Wenbing Huang , Minnan Luo , Qinghua Zheng , Yu Rong , Tingyang Xu , Junzhou Huang

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…

Machine Learning · Computer Science 2024-01-23 Jaeyoon Sim , Sooyeon Jeon , InJun Choi , Guorong Wu , Won Hwa Kim

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

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

The Transformer architecture has revolutionized deep learning through its Self-Attention mechanism, which effectively captures contextual information. However, the memory footprint of Self-Attention presents significant challenges for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Zohaib Khan , Muhammad Khaquan , Omer Tafveez , Burhanuddin Samiwala , Agha Ali Raza

This work examines the problem of graph learning over a diffusion network when data can be collected from a limited portion of the network (partial observability). The main question is to establish technical guarantees of consistent…

Statistics Theory · Mathematics 2020-06-08 Vincenzo Matta , Augusto Santos , Ali H. Sayed

Knowledge graph (KG) embedding methods learn geometric representations of entities and relations to predict plausible missing knowledge. These representations are typically assumed to capture rule-like inference patterns. However, our…

Artificial Intelligence · Computer Science 2025-07-29 Aleksandar Pavlovic , Emanuel Sallinger , Steven Schockaert

Traditional computer vision approaches, based on neural networks (NN), are typically trained on a large amount of image data. By minimizing the cross-entropy loss between a prediction and a given class label, the NN and its visual embedding…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Sebastian Monka , Lavdim Halilaj , Stefan Schmid , Achim Rettinger

Estimating the structure of directed acyclic graphs (DAGs) of features (variables) plays a vital role in revealing the latent data generation process and providing causal insights in various applications. Although there have been many…

Machine Learning · Computer Science 2024-03-06 Shaohua Fan , Shuyang Zhang , Xiao Wang , Chuan Shi

Incorporating Knowledge Graphs (KG) into recommeder system has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs).…

Information Retrieval · Computer Science 2022-08-23 Ding Zou , Wei Wei , Ziyang Wang , Xian-Ling Mao , Feida Zhu , Rui Fang , Dangyang Chen

A few models have tried to tackle the link prediction problem, also known as knowledge graph completion, by embedding knowledge graphs in comparably lower dimensions. However, the state-of-the-art results are attained at the cost of…

Machine Learning · Computer Science 2022-11-29 Peyman Baghershahi , Reshad Hosseini , Hadi Moradi

In this work, we are interested in structure learning for a set of spatially distributed dynamical systems, where individual subsystems are coupled via latent variables and observed through a filter. We represent this model as a directed…

Artificial Intelligence · Computer Science 2016-11-03 Oliver M. Cliff , Mikhail Prokopenko , Robert Fitch

Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning approaches such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Xuehai He , Xin Eric Wang

Continual learning in computer vision faces the critical challenge of catastrophic forgetting, where models struggle to retain prior knowledge while adapting to new tasks. Although recent studies have attempted to leverage the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xusheng Cao , Haori Lu , Linlan Huang , Fei Yang , Xialei Liu , Ming-Ming Cheng

Graph Transformers (GTs) have emerged as powerful architectures for graph-structured data, yet remain constrained by rigid designs and lack quantifiable interpretability. Current state-of-the-art GTs commit to fixed GNN types across all…

Machine Learning · Computer Science 2025-11-03 Shruti Sarika Chakraborty , Peter Minary

Multi-sourced datasets are common in studies of variable interactions, for example, individual-level fMRI integration, cross-domain recommendation, etc, where each source induces a related but distinct dependency structure. Joint learning…

Methodology · Statistics 2025-12-08 Shixiang Liu , Yanhang Zhang , Zhifan Li , Jianxin Yin