Neural Information Processing Systems http://nips.cc/

We build such explanations and counterfactuals iteratively using constraint solving techniques and a heuristic based on feature-level sensitivity ranking.

One of them is WN18RR [8], which is a wordnet subset containing40,943 entities, 11 relations, and86,835 training triples. The other is FB15k-237 [21], which is a Freebase subset containing 14,541 entities, 237 relations, and272,115 training triples. Random walks onhypergraphs with edge-dependent vertex weights.

Over the course of 2025, we had the pleasure of finding out more about a whole range of AI topics from researchers around the world. Here, we highlight some of our favourite interviews from the past 12 months. We caught up with Erica Kimei to find out about her research studying gas emissions from agriculture, specifically ruminant livestock. Erica combines machine learning and remote sensing technology to monitor and forecast such emissions. We spoke to Yuki Mitsufuji, Lead Research Scientist at Sony AI, to find out more about two pieces of research that his team presented at the Conference on Neural Information Processing Systems (NeurIPS 2024).

The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we extend NGU to multi-agent environments and evaluate its performance in the simple_tag environment from the PettingZoo suite. Compared to a multi-agent DQN baseline, NGU achieves moderately higher returns and more stable learning dynamics. We investigate three design choices: (1) shared replay buffer versus individual replay buffers, (2) sharing episodic novelty among agents using different k thresholds, and (3) using heterogeneous values of the beta parameter. Our results show that NGU with a shared replay buffer yields the best performance and stability, highlighting that the gains come from combining NGU intrinsic exploration with experience sharing. Novelty sharing performs comparably when k = 1 but degrades learning for larger values. Finally, heterogeneous beta values do not improve over a small common value. These findings suggest that NGU can be effectively applied in multi-agent settings when experiences are shared and intrinsic exploration signals are carefully tuned.