no code implementations • 13 Feb 2024 • Xuexin Chen, Ruichu Cai, Zhengting Huang, Yuxuan Zhu, Julien Horwood, Zhifeng Hao, Zijian Li, Jose Miguel Hernandez-Lobato
We investigate the problem of explainability in machine learning. To address this problem, Feature Attribution Methods (FAMs) measure the contribution of each feature through a perturbation test, where the difference in prediction is compared under different perturbations. However, such perturbation tests may not accurately distinguish the contributions of different features, when their change in prediction is the same after perturbation. In order to enhance the ability of FAMs to distinguish different features' contributions in this challenging setting, we propose to utilize the probability (PNS) that perturbing a feature is a necessary and sufficient cause for the prediction to change as a measure of feature importance. Our approach, Feature Attribution with Necessity and Sufficiency (FANS), computes the PNS via a perturbation test involving two stages (factual and interventional). In practice, to generate counterfactual samples, we use a resampling-based approach on the observed samples to approximate the required conditional distribution. Finally, we combine FANS and gradient-based optimization to extract the subset with the largest PNS. We demonstrate that FANS outperforms existing feature attribution methods on six benchmarks.
no code implementations • 26 Jun 2023 • Wenlin Chen, Julien Horwood, Juyeon Heo, José Miguel Hernández-Lobato
This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks.
no code implementations • 29 Apr 2020 • Julien Horwood, Emmanuel Noutahi
The fundamental goal of generative drug design is to propose optimized molecules that meet predefined activity, selectivity, and pharmacokinetic criteria.
no code implementations • 25 Sep 2019 • Emmanuel Noutahi, Dominique Beani, Julien Horwood, Prudencio Tossou
Recent work in graph neural networks (GNNs) has led to improvements in molecular activity and property prediction tasks.
no code implementations • 28 May 2019 • Emmanuel Noutahi, Dominique Beaini, Julien Horwood, Sébastien Giguère, Prudencio Tossou
We benchmark LaPool on molecular graph prediction and understanding tasks and show that it outperforms recent GNNs.