Timezone: »
Graph Neural Networks (GNNs) are a tantalizing way of modeling data which doesn't have a fixed structure. However, getting them to work as expected has had some twists and turns over the years.
This talk will have four components.
1. First, we'll briefly describe the Graph Mining team at Google.
2. Next, we'll focus on the Graph Mining team's work to make GNNs useful. We'll focus on challenges that we've identified and the solutions we've developed for them. Specifically, we'll highlight work that's led to more expressive graph convolutions, more robust models, and better graph structure. In addition, we'll highlight some new features available in our open source library for GNNs in TensorFLow, TF-GNN.
3. Second, we'll talk about other advances in Graph Mining from the group (including clustering, graph building, and privacy).
4. Finally, we'll have a tutorial section with quick demos covering TF-GNN, synthetic evaluation of GNNs with GraphWorld, and benchmarking for clustering tasks.
Sun 9:00 a.m. - 9:15 a.m.
|
Graph Mining at Google
(Expo talk)
SlidesLive Video » |
Vahab Mirrokni 🔗 |
Sun 9:15 a.m. - 9:20 a.m.
|
Challenges with Graph Neural Networks
(Expo Talk)
SlidesLive Video » |
Bryan Perozzi 🔗 |
Sun 9:20 a.m. - 9:40 a.m.
|
GraphWorld: Fake Graphs Bring Real Insights for GNNs
(Expo Talk)
SlidesLive Video » |
John Palowitch 🔗 |
Sun 9:45 a.m. - 9:50 a.m.
|
GraphWorld Q/A
(Q&A)
|
John Palowitch 🔗 |
Sun 9:50 a.m. - 9:55 a.m.
|
Break
|
🔗 |
Sun 9:55 a.m. - 10:20 a.m.
|
Discrete optimization with GNNs
(Expo Talk)
SlidesLive Video » |
Anton Tsitsulin 🔗 |
Sun 10:20 a.m. - 10:25 a.m.
|
Discrete optimization Q/A
(Q&A)
|
Anton Tsitsulin 🔗 |
Sun 10:25 a.m. - 10:40 a.m.
|
Robust GNNs
(Expo Talk)
SlidesLive Video » |
Bryan Perozzi 🔗 |
Sun 10:40 a.m. - 10:45 a.m.
|
Robust GNNs Q/A
(Q&A)
|
Bryan Perozzi 🔗 |
Sun 10:45 a.m. - 10:55 a.m.
|
TF-GNN: Graph Neural Networks Inside TensorFlow
(Expo Talk)
SlidesLive Video » |
Dustin Zelle 🔗 |
Sun 10:55 a.m. - 11:00 a.m.
|
TF-GNN Q/A
(Q&A)
|
Dustin Zelle 🔗 |
Sun 11:00 a.m. - 11:05 a.m.
|
Break
|
🔗 |
Sun 11:05 a.m. - 11:20 a.m.
|
New Challenges in Graph Mining: Scalability, Stability, and Privacy Applications
(Expo Talk)
SlidesLive Video » |
Vahab Mirrokni 🔗 |
Sun 11:20 a.m. - 11:25 a.m.
|
Graph Mining Q/A
(Q&A)
|
Vahab Mirrokni 🔗 |
Sun 11:25 a.m. - 11:40 a.m.
|
Advances in Graph Learning and Building
(Expo Talk)
SlidesLive Video » |
Rajesh Jayaram 🔗 |
Sun 11:40 a.m. - 11:45 a.m.
|
Graph Building Q/A
(Q&A)
|
Rajesh Jayaram 🔗 |
Sun 11:45 a.m. - 12:05 p.m.
|
Advances in Parallel Clustering
(Expo Talk)
SlidesLive Video » |
Laxman Dhulipala 🔗 |
Sun 12:05 p.m. - 12:10 p.m.
|
Clustering Q/A
(Q&A)
|
Laxman Dhulipala 🔗 |
Sun 12:10 p.m. - 12:15 p.m.
|
Break
|
🔗 |
Sun 12:15 p.m. - 12:45 p.m.
|
Advances in Private Algorithms: Clustering and Graph Mining
(Expo Talk)
SlidesLive Video » |
Alessandro Epasto · Peilin Zhong 🔗 |
Sun 12:45 p.m. - 12:50 p.m.
|
Private Algorithms Q/A
(Q&A)
|
Peilin Zhong · Alessandro Epasto · Vahab Mirrokni 🔗 |
Sun 12:50 p.m. - 12:55 p.m.
|
Break
|
🔗 |
Sun 12:55 p.m. - 1:10 p.m.
|
A simple introduction to TF-GNN models
(Expo Talk)
SlidesLive Video » |
Dustin Zelle 🔗 |
Sun 1:10 p.m. - 1:25 p.m.
|
Algorithmic Benchmarking with GBBS
(Expo Talk)
SlidesLive Video » |
Laxman Dhulipala 🔗 |
Sun 1:25 p.m. - 1:40 p.m.
|
Benchmarking GNNs with GraphWorld
(Expo Talk)
SlidesLive Video » |
John Palowitch 🔗 |
Sun 1:40 p.m. - 1:45 p.m.
|
Closing Remarks
(Expo Talk)
SlidesLive Video » |
Vahab Mirrokni 🔗 |
Author Information
Bryan Perozzi (Google AI)
Vahab Mirrokni (Google Research)
More from the Same Authors
-
2022 Poster: Tight and Robust Private Mean Estimation with Few Users »
Shyam Narayanan · Vahab Mirrokni · Hossein Esfandiari -
2022 Oral: Tight and Robust Private Mean Estimation with Few Users »
Shyam Narayanan · Vahab Mirrokni · Hossein Esfandiari -
2022 Poster: Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances »
Vincent Cohen-Addad · Vahab Mirrokni · Peilin Zhong -
2022 Spotlight: Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances »
Vincent Cohen-Addad · Vahab Mirrokni · Peilin Zhong -
2022 : Closing Remarks »
Vahab Mirrokni -
2022 : Private Algorithms Q/A »
Peilin Zhong · Alessandro Epasto · Vahab Mirrokni -
2022 : Graph Mining Q/A »
Vahab Mirrokni -
2022 : New Challenges in Graph Mining: Scalability, Stability, and Privacy Applications »
Vahab Mirrokni -
2022 : Robust GNNs Q/A »
Bryan Perozzi -
2022 : Robust GNNs »
Bryan Perozzi -
2022 : Challenges with Graph Neural Networks »
Bryan Perozzi -
2022 : Graph Mining at Google »
Vahab Mirrokni -
2021 Poster: Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time »
Laxman Dhulipala · David Eisenstat · Jakub Łącki · Vahab Mirrokni · Jessica Shi -
2021 Spotlight: Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time »
Laxman Dhulipala · David Eisenstat · Jakub Łącki · Vahab Mirrokni · Jessica Shi -
2021 Poster: Regularized Online Allocation Problems: Fairness and Beyond »
Santiago Balseiro · Haihao Lu · Vahab Mirrokni -
2021 Spotlight: Regularized Online Allocation Problems: Fairness and Beyond »
Santiago Balseiro · Haihao Lu · Vahab Mirrokni -
2021 Poster: Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing »
Yuan Deng · Sébastien Lahaie · Vahab Mirrokni · Song Zuo -
2021 Spotlight: Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing »
Yuan Deng · Sébastien Lahaie · Vahab Mirrokni · Song Zuo -
2020 Poster: Robust Pricing in Dynamic Mechanism Design »
Yuan Deng · Sébastien Lahaie · Vahab Mirrokni -
2020 Poster: Dual Mirror Descent for Online Allocation Problems »
Santiago Balseiro · Haihao Lu · Vahab Mirrokni -
2020 Poster: Bandits with Adversarial Scaling »
Thodoris Lykouris · Vahab Mirrokni · Renato Leme -
2019 Poster: Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity »
Matthew Fahrbach · Vahab Mirrokni · Morteza Zadimoghaddam -
2019 Poster: Categorical Feature Compression via Submodular Optimization »
Mohammad Hossein Bateni · Lin Chen · Hossein Esfandiari · Thomas Fu · Vahab Mirrokni · Afshin Rostamizadeh -
2019 Oral: Categorical Feature Compression via Submodular Optimization »
Mohammad Hossein Bateni · Lin Chen · Hossein Esfandiari · Thomas Fu · Vahab Mirrokni · Afshin Rostamizadeh -
2019 Oral: Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity »
Matthew Fahrbach · Vahab Mirrokni · Morteza Zadimoghaddam -
2019 Poster: MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing »
Sami Abu-El-Haija · Bryan Perozzi · Amol Kapoor · Nazanin Alipourfard · Kristina Lerman · Hrayr Harutyunyan · Greg Ver Steeg · Aram Galstyan -
2019 Poster: Distributed Weighted Matching via Randomized Composable Coresets »
Sepehr Assadi · Mohammad Hossein Bateni · Vahab Mirrokni -
2019 Oral: MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing »
Sami Abu-El-Haija · Bryan Perozzi · Amol Kapoor · Nazanin Alipourfard · Kristina Lerman · Hrayr Harutyunyan · Greg Ver Steeg · Aram Galstyan -
2019 Oral: Distributed Weighted Matching via Randomized Composable Coresets »
Sepehr Assadi · Mohammad Hossein Bateni · Vahab Mirrokni -
2018 Poster: Parallel and Streaming Algorithms for K-Core Decomposition »
Hossein Esfandiari · Silvio Lattanzi · Vahab Mirrokni -
2018 Poster: Accelerating Greedy Coordinate Descent Methods »
Haihao Lu · Robert Freund · Vahab Mirrokni -
2018 Poster: Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions »
Shuaiwen Wang · Wenda Zhou · Haihao Lu · Arian Maleki · Vahab Mirrokni -
2018 Oral: Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions »
Shuaiwen Wang · Wenda Zhou · Haihao Lu · Arian Maleki · Vahab Mirrokni -
2018 Oral: Accelerating Greedy Coordinate Descent Methods »
Haihao Lu · Robert Freund · Vahab Mirrokni -
2018 Oral: Parallel and Streaming Algorithms for K-Core Decomposition »
Hossein Esfandiari · Silvio Lattanzi · Vahab Mirrokni -
2018 Poster: Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy »
Shipra Agarwal · Morteza Zadimoghaddam · Vahab Mirrokni -
2018 Oral: Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy »
Shipra Agarwal · Morteza Zadimoghaddam · Vahab Mirrokni -
2017 Poster: Tight Bounds for Approximate Carathéodory and Beyond »
Vahab Mirrokni · Renato Leme · Adrian Vladu · Sam Wong -
2017 Talk: Tight Bounds for Approximate Carathéodory and Beyond »
Vahab Mirrokni · Renato Leme · Adrian Vladu · Sam Wong