Report time:10month10No. (Monday) morning9：00-10:00
Moderator: Wu Wei
Tencent conference number:534-494-879
Title: Large-Scale Graph Comparative Bet365 Poker
Abstract:Deep Bet365 Poker on graphs has attracted significant interest recently. However, most of the works have focused on (semi-) supervised Bet365 Poker, resulting in shortcomings, including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised Bet365 Poker (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending Bet365 Poker paradigm for graph data. However, current self-supervised Bet365 Poker methods, especially graph contrastive Bet365 Poker (GCL) methods, require heavy computations in their designs, hindering them from scaling to large graphs. In this talk, I will introduce our recent development in scaling up graph contrast Bet365 Poker for graph data. By examining existing graph contrast Bet365 Poker methods and pinpointing their defects, we propose a new group discrimination method (to appear in NeurIPS 2022), which is orders of magnitude (10,000+ faster than GCL baselines) while consuming much less memory. The new solution opens a new door to self-supervised Bet365 Poker for large-scale datasets in the graph domain and potentially in other areas such as vision and language.
Personal introduction: Pan Shirui, Australian Funding CommitteeOutstanding young man,Full Bet365 Poker at Griffith University (Full Bet365 Poker）。Selected as the most influential scholar in the world AAAI/IJCAI for two consecutive years，Selected into the top 2% of scientists in the world (2021)， Received the 2021 Monash University School of Information Technology Research Excellence Award (Early Year Researchers)。Guiding students to win the Best Student Paper Award at the Data Mining Conference ICDM (2020)，Won the Best Paper Nomination Award at the 2020 JCDL Conference。at NeurIPS、ICML、KDD、TPAMI、TKDE、TNNLSetc.Published high-level papers150 articles。Also serves as TPAMI, TNNNLS, Reviewer of journals in TKDE and other fields，RenIJCAI, AAAI, KDD, WWW, Member of CVPR and other (senior) program committees。Google Scholar citation11,000+，Hindex(H-Index) 43。The main Bet365 Poker direction is data mining、Machine Bet365 Poker. It was published inTNNNLS-2021Review papers on Bet365 Poker neural networks cited as high as 22366_223824000+，Posted onKDD、IJCAI、AAAI、CIKMWaiting for top conferences8Articles were rated as the Bet365 Poker (Bet365 Poker）。
