Human-inspired method improves learning in large decision spaces
Human-inspired, Task-Dimension-Guided Exploration for Efficient Learning in High Dimensions
Machine Learning
Summary
Exploring many options in complex problems is hard for computers but easy for humans, who focus on important features first. This paper presents TDGE, an algorithm inspired by how humans pick relevant aspects to explore efficiently. TDGE works in steps: choosing important feature groups, then detailed features, and finally making decisions based on those features. Tests on movie, music, and product recommendation datasets show that TDGE learns faster and better than other methods, even when starting with little data.
What this means in practice
- •For ecommerce engineers: Improve product recommendations by focusing exploration on key product features to quickly personalize suggestions for new users.
- •For music streaming platform developers: Enhance cold-start music recommendations by guiding exploration toward relevant user preferences and music attributes.
Authors
Fanyu Zhu, Jiahui An, Ni Ji
Abstract
Efficient exploration in high-dimensional decision spaces remains a central challenge for decision-making systems. Humans, in contrast, can navigate large decision spaces with remarkable efficiency. Recent behavioral studies suggest that humans reduce dimensionality in large decision spaces by probing candidate feature dimensions, identifying reward-relevant ones, and restricting the effective decision space. Inspired by this mechanism, we propose TDGE (Task-Dimension-Guided Exploration), a human-inspired, model-agnostic algorithm with an automatically constructed task-dimension--feature--item hierarchy. TDGE follows a top-down exploration strategy: it first selects task-relevant feature dimensions, then identifies informative features within those dimensions, and finally recommends concrete items based on the selected features. Experiments on MovieLens-20M, Last.fm, and Amazon recommendation datasets show that TDGE substantially improves exploration efficiency and cold-start adaptation over baseline algorithms. Comparisons with other structured algorithms and ablation studies attribute these gains to TDGE's hierarchical structure and semantic feature-space exploration, with robust results across clustering methods and hierarchy depths. Recommendation-trajectory visualizations also show exploration patterns similar to human dimension-guided behavior.