Interactive Visualization Recommendation with Hier-SUCB

2025-02-05

AI Summary

Existing personalized visualization recommendation methods suffer from limited interactivity and reliance on static initial data, rendering them inadequate for cold-start scenarios and dynamic user preference drift. To address these limitations, we propose an interactive recommendation system that dynamically refines recommendations by real-time incorporation of user feedback. Our core contribution is Hier-SUCB—a novel hierarchical contextual combinatorial semi-bandit framework specifically designed for visualization recommendation—the first of its kind with a theoretically proven tighter cumulative regret bound scaling sublinearly in the action-space dimension. The method integrates hierarchical semantic modeling, interactive online learning, and joint optimization of visualization encoding and ranking. Empirical evaluation demonstrates that our approach achieves accuracy comparable to offline models while significantly outperforming state-of-the-art bandit-based methods; it supports millisecond-level response latency and continuous adaptation to evolving user preferences.

Technology Category

Machine Learning: Online Learning & BanditsData Mining & Knowledge Management: Data Visualization & SummarizationReasoning under Uncertainty: Stochastic Optimization

Application Category

User Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Visualization recommendation aims to enable rapid visual analysis of massive datasets. In real-world scenarios, it is essential to quickly gather and comprehend user preferences to cover users from diverse backgrounds, including varying skill levels and analytical tasks. Previous approaches to personalized visualization recommendations are non-interactive and rely on initial user data for new users. As a result, these models cannot effectively explore options or adapt to real-time feedback. To address this limitation, we propose an interactive personalized visualization recommendation (PVisRec) system that learns on user feedback from previous interactions. For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual combinatorial semi-bandit in the PVisRec setting. Theoretically, we show an improved overall regret bound with the same rank of time but an improved rank of action space. We further demonstrate the effectiveness of Hier-SUCB through extensive experiments where it is comparable to offline methods and outperforms other bandit algorithms in the setting of visualization recommendation.

Problem

• Interactive visualization recommendation system
• Real-time user feedback adaptation
• Improved regret bound analysis

Innovation

• Interactive visualization recommendation system
• Hier-SUCB algorithm for real-time feedback
• Improved regret bound in action space