Attention to task structure for cognitive flexibility
Xiaoyu K. Zhang, Mehdi Senoussi, Tom Verguts

TL;DR
This paper investigates how environmental structure influences cognitive flexibility in multi-task learning, highlighting the interaction between environment connectivity and attention-based models in improving generalization and stability.
Contribution
It introduces a graph-theory based multi-task environment and compares attention models to MLPs, revealing environment connectivity's critical role in cognitive flexibility.
Findings
Rich environments enhance generalization and stability.
Connectivity between tasks significantly affects model performance.
Attention models benefit more from environment connectivity than MLPs.
Abstract
Humans and artificial agents must often learn and switch between multiple tasks in dynamic environments. Success in such settings requires cognitive flexibility: the ability to retain prior knowledge (cognitive stability) while also transferring it to novel tasks (cognitive generalization). Cognitive flexibility research has largely focused on the role of model architecture to achieve these complementary goals. However, it is less well understood how the structure of the environment itself influences cognitive flexibility, and how it interacts with model architecture. To address this gap, we design a multi-task learning environment in which tasks are defined by a combination of two cue dimensions, allowing us to characterize the environment with graph-theory methods. We also introduce gating-based (multiplicative) and concatenation-based attention models that can decompose tasks into…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
