← Search

James Kirkpatrick

3 accepted papers

2022

Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond

ICLR 2022poster

In this paper we show that simple noisy regularisation can be an effective way to address oversmoothing. We first argue that regularisers ad-dressing oversmoothing should both penalise node latent similarity and encourage meaningful node representations. From this observation we derive “Noisy Nodes”…

Cited by 147SourcePDFScholar
2017

Distral: Robust multitask reinforcement learning

NeurIPS 2017poster

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network parameters, where efficiency may be improved through transfe…

Cited by 677SourcePDFScholar
2016

The Forget-me-not Process

NeurIPS 2016poster

We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources. Our method works by taking a Bayesian approach to partition a stream of data into postulated task-specific segments, while sim…

Cited by 31SourcePDFScholar