Graph Neural Network Bandits
Nov 28, 2022
Speakers
Parnian Kassraie
Speaker · 1 follower
Andreas Krause
Speaker · 6 followers
Ilija Bogunovic
Speaker · 0 followers
About
We consider the bandit optimization problem with the reward function defined over graph-structured data. This problem has important applications in molecule design and drug discovery, where the reward is naturally invariant to graph permutations. The key challenges in this setting are scaling to large domains, and to graphs with many nodes. We resolve these challenges by embedding the permutation invariance into our model. In particular, we show that graph neural networks (GNNs) can be used to estimate the reward function, assuming it resides in the Reproducing Kernel Hilbert Space of a permutation-invariant additive kernel. By establishing a novel connection between such kernels and the graph neural tangent kernel (GNTK), we introduce the first GNN confidence bound and use it to design a phased-elimination algorithm with sublinear regret. Our regret bound depends on the GNTK's maximum information gain, which we also provide a bound for. Perhaps surprisingly, even though the reward function depends on all N node features, our guarantees are independent of the number of graph nodes N. Empirically, our approach exhibits competitive performance and scales well on graph-structured domains.We consider the bandit optimization problem with the reward function defined over graph-structured data. This problem has important applications in molecule design and drug discovery, where the reward is naturally invariant to graph permutations. The key challenges in this setting are scaling to large domains, and to graphs with many nodes. We resolve these challenges by embedding the permutation invariance into our model. In particular, we show that graph neural networks (GNNs) can be used to e…
Organizer
NeurIPS 2022
Account · 966 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Solving a Special Type of Optimal Transport Problem by a Modified Hungarian Algorithm
Watch later
Yiling Xie, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
PAINT: Patching Open-Vocabulary Models by Interpolating Weights
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
GriddlyJS: A Web IDE for Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Train Offline, Test Online: A Real Robot Learning Benchmark
Watch later
Gaoyue Zhou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator
Watch later
Zifan Shi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%