In recent years, the field of machine learning has witnessed a surge of interest in utilizing graph neural networks (GNNs) for analyzing and processing graph data. This powerful expressive capability of GNNs has sparked significant research activity in the domain of Graph Machine Learning (Graph ML).

The growing enthusiasm for Graph ML within the machine learning community has turned it into a prominent and highly-discussed topic at various deep neural network conferences. Researchers and practitioners are recognizing the potential of Graph ML to address a wide range of real-world problems, including social network analysis, recommendation systems, drug discovery, molecular chemistry, computer vision, and more. By leveraging the inherent structural relationships present in graph data, Graph ML techniques enable more effective and accurate analysis and predictions.

To foster collaboration, knowledge sharing, and intellectual growth, the Learning on Graphs Seminar (LOGS) has emerged as a valuable initiative within the field. LOGS organizes seminars on an irregular basis, bringing together experts, frontline researchers, and authors of top conference papers in the domain of graph learning. The primary aim of LOGS is to create a platform that facilitates mutual communication, encourages insightful discussions, and promotes continuous learning among participants.

By inviting renowned experts and prominent figures in the field, LOGS ensures that the seminars provide cutting-edge insights and the latest advancements in Graph ML. Participants have the opportunity to engage in meaningful discussions, exchange ideas, and gain valuable knowledge from the forefront of graph learning research. The seminar format allows for a collaborative environment where participants can explore new approaches, share their findings, and collectively push the boundaries of Graph ML.

LOGS aims to catalyze innovation, inspiring researchers to explore novel techniques, develop robust algorithms, and tackle complex challenges associated with graph data analysis. Through LOGS, researchers can stay up-to-date with the rapidly evolving landscape of Graph ML and make meaningful contributions to this exciting and impactful field.

Find and Join Us

Committees and Organizers

Previous Activities

Date Topic Speaker Video
January 15, 2023 Application of geometric graph neural network in scientific computation Wenbing Huang(Renmin University of China) Bilibili, Youtube
January 14, 2023 Research Progress of Heterogeneous Graph Neural Network Xinyu Fu(Chinese University of Hong Kong MISC Lab) Bilibili, Youtube
January 14, 2023 See (picture) comparative learning from the perspective of spectrum Yifei Zhang(Chinese University of Hong Kong MISC Lab) Bilibili, Youtube
January 14, 2023 Binary representation of graph features for online Top-K recommendation Yankai Chen(Chinese University of Hong Kong MISC Lab) Bilibili, Youtube
January 14, 2023 Hyperbolic graph neural network: methods and applications Menglin Yang(Chinese University of Hong Kong MISC Lab) Bilibili, Youtube
January 7, 2023 From Classical Convex Optimization Algorithm to Graph Neural Network Quan Gan(Amazon Cloud Technology Shanghai Institute of Artificial Intelligence) Bilibili, Youtube
January 7, 2023 Application of graph neural network in visual representation learning and time series analysis Tianjun Xiao&Tong He(Amazon Cloud Technology Shanghai Institute of Artificial Intelligence) Bilibili, Youtube
January 7, 2023 The latest development of the neural network system DGL MinJie Wang&Zhenkun Cai(https://dl.ccf.org.cn/albumList/5752875678795776?_ack=1&https://scholar.lanfanshu.cn/citations?user=sOjbP8kAAAAJ&hl=zh-CN&oi=ao) Bilibili, Youtube
November 12, 2022 Design space and open source algorithm library of graph neural network Tianyu Zhao(Beijing University of Posts and Telecommunications) Bilibili, Youtube
November 12, 2022 Figure Structure Learning Ruijia Wang(Beijing University of Posts and Telecommunications) Bilibili, Youtube
November 12, 2022 Diagram causal representation learning Shaohua Fan(Beijing University of Posts and Telecommunications) Bilibili, Youtube
November 5, 2022 Figure Negative Sampling in Comparative Learning Jun Xia(Westlake University) Bilibili, Youtube
November 5, 2022 Self Supervised Learning on Maps: Review and Prospect Lirong Wu(Westlake University) Bilibili, Youtube
November 12, 2022 GAMMA Lab Introduction Chuan Shi(Beijing University of Posts and Telecommunications) Bilibili, Youtube
October 29, 2022 Out-of-Distribution Generalized Graph Neural Network Ziwei Zhang(Tsinghua University) Bilibili, Youtube
October 29, 2022 Out-of-Distribution Generalization and Extrapolation on Graphs Qitian Wu(Shanghai Jiaotong University) Bilibili, Youtube
October 23, 2022 Graphic neural network and anomaly detection Yue Zhao(Carnegie Mellon University) Bilibili, Youtube
October 15, 2022 Figure “Generality” and “Personality” of Neural Network Xiao Wang (Beijing University of Posts and Telecommunications) Bilibili, Youtube
October 15, 2022 Rethinking and Scaling Up Graph Contrastive Learning Pan Shirui (Griffith University) Bilibili, Youtube
September 25, 2022 Graph Neural Networks with Geometric and Topologic Structures Tengfei Ma (IBM Watson Research Institute) Bilibili, Youtube
September 25, 2022 Explainability of Graph Neural Networks Xiang Wang (University of Science and Technology of China) Bilibili, Youtube
September 4, 2022 Robust Machine Learning on Graph Data Jiarong Xu (Fudan University) Bilibili, Youtube
September 4, 2022 Graph Machine Learning Against Financial Fraud Adversarial Attacks Xiang Ao (Institute of computing, Chinese Academy of Sciences) Bilibili, Youtube
September 3, 2022 A Preliminary Study of Set Theory: From Point Sets to Infinite Time Turing Machines Jin Du (The Chinese University of Hong Kong) Bilibili, Youtube
August 27, 2022 Human Memories as Repositories of Events: Event Graph Knowledge Acquisition Manling Li (University of Illinois Urbana-Champaign） Bilibili, Youtube
August 27, 2022 Knowledge Graph Reasoning with Graph Neural Networks ZhaoCheng Zhu (Mila-Quebec AI Institute, University of Montreal） Bilibili, Youtube
August 12, 2022 Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning Xiang Fu (MIT ） Bilibili, Youtube
August 12, 2022 EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction Hannes Stärk (MIT ） Bilibili, Youtube
August 6, 2022 Application of Hyperbolic Graph Neural Network in Recommendation System and Quantization Menglin Yang (The Chinese University of Hong Kong） Bilibili, Youtube
August 6, 2022 Hyperbolic Representation Learning and Knowledge Graph Rex Ying (Yale University） Bilibili, Youtube
July 30, 2022 Graph data modeling and analysis from the perspective of curvature Wentao Zhang (Mila) Bilibili, Youtube
July 26, 2022 Graph Geometry Learning and Drug Discovery Jian Tang (Montreal Institute of Algorithms, Canada University of Montreal Business School) Bilibili, Youtube
July 23, 2022 An overview of Graph Generative Models and Their Applications on Molecular Generation Tingyang Xu (Tencent AI Lab) Bilibili, Youtube
July 23, 2022 Graph Neural Network and Reinforcement Learning Furui Liu (Zhijiang Lab) Bilibili, Youtube
July 16, 2022 Graph data modeling and analysis from the perspective of curvature Min Zhou (Huawei Noah’s Ark laboratory) Bilibili, Youtube
July 16, 2022 Rethinking Graph Neural Networks for Anomaly Detection Jia Li (The Hong Kong University of Science and Technology) Bilibili, Youtube
July 9, 2022 Graph Neural Networks Enter the Transformer Era Shuxin Zheng (Microsoft Research Asia) Bilibili, Youtube
July 9, 2022 How Powerful are Spectral Graph Neural Networks? Muhan Zhang (Peking University) Bilibili, Youtube
July 2, 2022 Optimization Perspectives on Graph Neural Networks Zengfeng Huang (Fudan University) Bilibili, Youtube
July 2, 2022 Exploration of the Latest Paradigm of Graph Neural Network Yu Rong (Tencent AI Lab) Bilibili, Youtube