The Programming Club of Computing Center at Ilia State University presents a weekly series of meetings for people interested in Computer Science.
The next topic for February 2, 2022, is “Bootstrapped Self-Supervised Representation Learning on Graphs”
About the meeting:
Self-supervised graph representation learning aims to construct meaningful representations of graph-structured data in the absence of labels.
Current state-of-the-art methods are based on contrastive learning and depend heavily on the construction of augmentations and negative examples. Achieving peak performance requires computation quadratic in the number of nodes, which can be prohibitively expensive.
In this talk, we will present Bootstrapped Graph Latents (BGRL) a method for self-supervised graph representation learning that gets rid of this potentially quadratic bottleneck.
We show that BGRL outperforms or matches previous methods on several established benchmark datasets while consuming 2-10x less memory. Moreover, it enables the effective usage of more expressive GNN architectures, allowing us to further improve the state of the art.
Finally, we will present our recent results on applying BGRL to the very large-scale data regime, in the OGB-LSC KDD Cup, where it was key to our entry is among the top 3 awardees on our track.
About the Speaker:
Shantanu Thakoor, Research Engineer at DeepMind London
Shantanu is a Research Engineer working at DeepMind London. His primary research interests are in graph representation learning and reinforcement learning. Prior to this, he received his MS from Stanford University and B.Tech. from IIT Bombay.
Meeting time: February 02, 19:00 p.m.
Meeting language: English
Registration deadline: February 02, 18:00 p.m.
Meeting place: Zoom and FB Live
The meeting link will be sent to participants at the email address specified during registration.
Attendance is free.