DeepAI
Log In Sign Up

Graph Neural Network Bandits

07/13/2022
by   Parnian Kassraie, et al.
42

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. While 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/07/2021

Neural Contextual Bandits without Regret

Contextual bandits are a rich model for sequential decision making given...
09/26/2013

Finite-Time Analysis of Kernelised Contextual Bandits

We tackle the problem of online reward maximisation over a large finite ...
09/07/2022

Dual Instrumental Method for Confounded Kernelized Bandits

The contextual bandit problem is a theoretically justified framework wit...
01/25/2023

Graph Neural Tangent Kernel: Convergence on Large Graphs

Graph neural networks (GNNs) achieve remarkable performance in graph mac...
05/28/2022

Going Deeper into Permutation-Sensitive Graph Neural Networks

The invariance to permutations of the adjacency matrix, i.e., graph isom...
08/30/2021

Adversarial Stein Training for Graph Energy Models

Learning distributions over graph-structured data is a challenging task ...