Preference Elicitation with Soft Attributes in Interactive Recommendation
This addresses the challenge for users who wish to describe preferences using soft attributes in interactive recommendation, representing an incremental advancement by integrating existing techniques.
The paper tackles the problem of preference elicitation in interactive recommender systems by developing methods that accommodate soft attributes without ground-truth semantics, using concept activation vectors to combine item and attribute queries, and demonstrates effectiveness on synthetic and real-world datasets with improved recommendation quality.
Preference elicitation plays a central role in interactive recommender systems. Most preference elicitation approaches use either item queries that ask users to select preferred items from a slate, or attribute queries that ask them to express their preferences for item characteristics. Unfortunately, users often wish to describe their preferences using soft attributes for which no ground-truth semantics is given. Leveraging concept activation vectors for soft attribute semantics, we develop novel preference elicitation methods that can accommodate soft attributes and bring together both item and attribute-based preference elicitation. Our techniques query users using both items and soft attributes to update the recommender system's belief about their preferences to improve recommendation quality. We demonstrate the effectiveness of our methods vis-a-vis competing approaches on both synthetic and real-world datasets.