Expo Workshop

The Mining and Learning with Graphs at Scale workshop focuses on methods for operating on massive information networks. We begin by highlighting applications of graph-based learning and graph algorithms for a wide range of areas such as detecting fraud and abuse, query clustering and duplication detection, image and multi-modal data analysis, privacy-respecting data mining and recommendation, and experimental design under interference.

The main body of the presentation is divided into three sections:

In our first segment, we cover graph learning and graph building algorithms which we apply to graphs with billions of nodes, and trillions of potential edges. We also discuss similarity ranking over graphs, and the clustering and community detection methods which power numerous industrial applications. This section concludes with a discussion of graph-based semi-supervised learning techniques.

Our second segment covers the application of neural networks to graph structured data through both positional graph embeddings and graph neural networks (GNNs). We present challenges, and recent results from our team on scalable inference algorithms for GNNs, methods for dealing with bias in graph data, and ensemble approaches to representing nodes which allow more modeling flexibility.

Our final segment discusses different techniques for working with massive graphs. We focus on how to take advantage of both single- and multi-machine parallelism to run algorithms on graphs of up to trillions of edges.

Chat is not available.


Timezone: »


Sun 10:00 a.m. - 10:20 a.m.
Introduction (Presentation) Video
Vahab Mirrokni
Sun 10:20 a.m. - 10:30 a.m.
Application Story: COVID Modeling (Presentation) Video
Amol Kapoor
Sun 10:30 a.m. - 10:35 a.m.
Application Story: Privacy (Presentation) Video
Alessandro Epasto
Sun 10:35 a.m. - 10:40 a.m.
Application Story: Experimental Design (Presentation) Video
Jean Pouget-Abadie
Sun 10:40 a.m. - 10:45 a.m.
Live Q/A (Break)
Sun 10:45 a.m. - 11:00 a.m.
Grale: Learning Graphs (Presentation) Video
Jonathan Halcrow
Sun 11:00 a.m. - 11:15 a.m.
Similarity Ranking (Presentation) Video
Alessandro Epasto
Sun 11:15 a.m. - 11:30 a.m.
Clustering At Scale (Presentation) Video
Vahab Mirrokni
Sun 11:30 a.m. - 11:40 a.m.
Community Detection (Presentation) Video
Jakub Lacki
Sun 11:40 a.m. - 11:55 a.m.
Label Propagation (Presentation) Video
Allan Heydon
Sun 11:55 a.m. - 12:00 p.m.
Live Q/A (Break)
Sun 12:00 p.m. - 12:20 p.m.
GNNs and Graph Embeddings (Presentation) Video
Bryan Perozzi
Sun 12:20 p.m. - 12:35 p.m.
PPRGo: GNNs at Scale (Presentation) Video
Amol Kapoor
Sun 12:35 p.m. - 12:50 p.m.
Debiasing GNNs (Presentation) Video
John Palowitch
Sun 12:50 p.m. - 1:00 p.m.
Learning Multiple Embeddings (Presentation) Video
Alessandro Epasto
Sun 1:00 p.m. - 1:05 p.m.
Live Q/A (Break)
Sun 1:05 p.m. - 1:20 p.m.
Tensorflow Infrastructure: Graph Tensor (Presentation) Video
Martin Blais
Sun 1:20 p.m. - 1:45 p.m.
Graph algorithms in the distributed setting (Presentation) Video
Jakub Lacki
Sun 1:45 p.m. - 1:55 p.m.
Multi-core parallel graph clustering (Presentation) Video
Jakub Lacki
Sun 1:55 p.m. - 2:05 p.m.
Q/A & Closing Remarks (Closing Remarks)