Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors
This work addresses the problem of enhancing recommendation accuracy by personalizing attribute semantics for users in interactive systems, representing an incremental advancement in leveraging interpretability methods for recommender tasks.
The paper tackles the challenge of inferring user semantic intent from open-ended attributes in interactive recommender systems by developing a framework using concept activation vectors (CAVs) to learn personalized semantics for subjective attributes, demonstrating improved recommendations through interactive critiquing on synthetic and real-world datasets.
Interactive recommender systems have emerged as a promising paradigm to overcome the limitations of the primitive user feedback used by traditional recommender systems (e.g., clicks, item consumption, ratings). They allow users to express intent, preferences, constraints, and contexts in a richer fashion, often using natural language (including faceted search and dialogue). Yet more research is needed to find the most effective ways to use this feedback. One challenge is inferring a user's semantic intent from the open-ended terms or attributes often used to describe a desired item, and using it to refine recommendation results. Leveraging concept activation vectors (CAVs) [26], a recently developed approach for model interpretability in machine learning, we develop a framework to learn a representation that captures the semantics of such attributes and connects them to user preferences and behaviors in recommender systems. One novel feature of our approach is its ability to distinguish objective and subjective attributes (both subjectivity of degree and of sense), and associate different senses of subjective attributes with different users. We demonstrate on both synthetic and real-world data sets that our CAV representation not only accurately interprets users' subjective semantics, but can also be used to improve recommendations through interactive item critiquing.