Results 261 to 270 of about 6,652,811 (287)

Graph Representation Learning

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021
Graphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be facilitated.
Wei Jin, Yao Ma, Yiqi Wang, Xiaorui Liu, Jiliang Tang, Yukuo Cen, Jiezhong Qiu, Jie Tang, Chuan Shi, Yanfang Ye, Jiawei Zhang, Philip S. Yu   +11 more
openaire   +1 more source

Robust and Consistent Anchor Graph Learning for Multi-View Clustering

IEEE Transactions on Knowledge and Data Engineering
Anchor-based multi-view graph clustering has recently gained popularity as an effective approach for clustering data with multiple views. However, existing methods have limitations in terms of handling inconsistent information and noise across views ...
Suyuan Liu, Qing Liao, Siwei Wang, Xinwang Liu, En Zhu   +4 more
semanticscholar   +1 more source

Blockchain Data Mining With Graph Learning: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
Blockchain data mining has the potential to reveal the operational status and behavioral patterns of anonymous participants in blockchain systems, thus providing valuable insights into system operation and participant behavior.
Yuxin Qi, Jun Wu, Hansong Xu, Mohsen Guizani   +3 more
semanticscholar   +1 more source

Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement prediction

Information Fusion
With the increasing availability of multimodal educational data, there is a growing need to effectively integrate and exploit multiple data sources to enhance student engagement prediction accuracy.
Ming Li, Xiaosheng Zhuang, Lu Bai, Weiping Ding   +3 more
semanticscholar   +1 more source

An Efficient Graph Learning System for Emotion Recognition Inspired by the Cognitive Prior Graph of EEG Brain Network

IEEE Transactions on Neural Networks and Learning Systems
Benefiting from the high-temporal resolution of electroencephalogram (EEG), EEG-based emotion recognition has become one of the hotspots of affective computing. For EEG-based emotion recognition systems, it is crucial to utilize state-of-the-art learning
Cunbo Li, Tian Tang, Yue Pan, Lei Yang, Shuhan Zhang, Zhaojin Chen, Peiyang Li, Dongrui Gao, Huafu Chen, Fali Li, Dezhong Yao, Zehong Cao, Peng Xu   +12 more
semanticscholar   +1 more source

Tensor-Based Adaptive Consensus Graph Learning for Multi-View Clustering

IEEE transactions on consumer electronics
Multi-view clustering has garnered considerable attention in recent years owing to its impressive performance in processing high-dimensional data. Most multi-view clustering models still encounter the following limitations.
Wei Guo, Hangjun Che, Man-Fai Leung
semanticscholar   +1 more source

A Survey of Data-Efficient Graph Learning

International Joint Conference on Artificial Intelligence
Graph-structured data, prevalent in domains ranging from social networks to biochemical analysis, serve as the foundation for diverse real-world systems.
Wei Ju, Siyu Yi, Yifan Wang, Qingqing Long, Junyu Luo, Zhiping Xiao, Ming Zhang   +6 more
semanticscholar   +1 more source

Hyperbolic Graph Learning for Social Recommendation

IEEE Transactions on Knowledge and Data Engineering
Social recommendation provides an auxiliary social network structure to enhance recommendation performances. By formulating user-user social network and user-item interaction graph, modern social recommendation architecture is built on learning user and ...
Yonghui Yang, Le Wu, Kun Zhang, Richang Hong, Hailin Zhou, Zhiqiang Zhang, Jun Zhou, Meng Wang   +7 more
semanticscholar   +1 more source

Deep Graph Learning

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020
Many real data come in the form of non-grid objects, i.e. graphs, from social networks to molecules. Adaptation of deep learning from grid-alike data (e.g. images) to graphs has recently received unprecedented attention from both machine learning and data mining communities, leading to a new cross-domain field---Deep Graph Learning (DGL).
Yu Rong, Tingyang Xu, Junzhou Huang, Wenbing Huang, Hong Cheng, Yao Ma, Yiqi Wang, Tyler Derr, Lingfei Wu, Tengfei Ma   +9 more
openaire   +1 more source

PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation

International Conference on Architectural Support for Programming Languages and Operating Systems
This paper introduces two extensions to the popular PyTorch machine learning framework, TorchDynamo and TorchInductor, which implement the torch.compile feature released in PyTorch 2. TorchDynamo is a Python-level just-in-time (JIT) compiler that enables
Jason Ansel, Edward Yang, Horace He, N. Gimelshein, Animesh Jain, Michael Voznesensky, Bin Bao, Peter Bell, D. Berard, Evgeni Burovski, Geeta Chauhan, Anjali Chourdia, W. Constable, Alban Desmaison, Zachary DeVito, Elias Ellison, W. Feng, Jiong Gong, Michael Gschwind, B. Hirsh, Sherlock Huang, Kshiteej Kalambarkar, Laurent Kirsch, Michael Lazos, M. Lezcano, Yanbo Liang, Jason Liang, Yinghai Lu, C. Luk, Bertrand A. Maher, Yunjie Pan, Christian Puhrsch, Matthias Reso, Mark-Albert Saroufim, Marcos Yukio Siraichi, Helen Suk, Shunting Zhang, Michael Suo, P. Tillet, Xu Zhao, Eikan Wang, Keren Zhou, Richard Zou, Xiaodong Wang, Ajit Mathews, W. Wen, Gregory Chanan, Peng Wu, Soumith Chintala   +48 more
semanticscholar   +1 more source