Hubert Pham
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hubert Pham has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- James Pine
Google Research, Mountain View, CA, USA
3 shared publications - Ambarish Jash
Google Research, Mountain View, CA, USA
2 shared publications - Chih-Wei Hsu
Google Inc, Mountain View, United States
2 shared publications - Craig Boutilier
Google research
2 shared publications - Krishna Sayana
Google Research, Mountain View, CA, USA
2 shared publications - Liam Hebert
University of Waterloo, Waterloo, Ontario, Canada
2 shared publications
Latest Publications
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2235-2244
FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2235-2244
Open AccessFLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2411-2420
Beyond Retrieval: Generating Narratives in Conversational Recommender Systems
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2411-2420
Open AccessBeyond Retrieval: Generating Narratives in Conversational Recommender Systems
- Open Access
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (4) , 1-37
Discovering Personalized Semantics for Soft Attributes in Recommender Systems Using Concept Activation Vectors
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. This is critical for recommender systems that wish to support users in their everyday, intuitive use of natural language 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 datasets that our CAV representation not only accurately interprets users’ subjective semantics but also can be used to improve recommendations through interactive item critiquing .
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (4) , 1-37
Open AccessDiscovering Personalized Semantics for Soft Attributes in Recommender Systems Using Concept Activation Vectors
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. This is critical for recommender systems that wish to support users in their everyday, intuitive use of natural language 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 datasets that our CAV representation not only accurately interprets users’ subjective semantics but also can be used to improve recommendations through interactive item critiquing .
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2925-2929
Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies
Evaluation of policies in recommender systems typically involves A/B live experiments on real users to assess a new policy's impact on relevant metrics. This "gold standard'' comes at a high cost, however, in terms of cycle time, user cost, and potential user retention. In developing policies for onboarding users, these costs can be especially problematic, since on-boarding occurs only once. In this work, we describe a simulation methodology used to augment (and reduce) the use of live experiments. We illustrate its deployment for the evaluation of preference elicitation algorithms used to onboard new users of the YouTube Music platform. By developing counterfactually robust user behavior models, and a simulation service that couples such models with production infrastructure, we can test new algorithms in a way that reliably predicts their performance on key metrics when deployed live.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2925-2929
Open AccessMinimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies
Evaluation of policies in recommender systems typically involves A/B live experiments on real users to assess a new policy's impact on relevant metrics. This "gold standard'' comes at a high cost, however, in terms of cycle time, user cost, and potential user retention. In developing policies for onboarding users, these costs can be especially problematic, since on-boarding occurs only once. In this work, we describe a simulation methodology used to augment (and reduce) the use of live experiments. We illustrate its deployment for the evaluation of preference elicitation algorithms used to onboard new users of the YouTube Music platform. By developing counterfactually robust user behavior models, and a simulation service that couples such models with production infrastructure, we can test new algorithms in a way that reliably predicts their performance on key metrics when deployed live.