Practical Diversified Recommendations on YouTube with Determinantal Point Processes

Wilhelm, Mark; Ramanathan, Ajith; Bonomo, Alexander; Jain, Sahil; H., Ed; Gillenwater, Jennifer

doi:10.1145/3269206.3272018

Cited by 108 publications

(85 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While our emphasis in studying setwise recommendations was its connections to elicitation, considerable attention has been paid to set-based recommendation in itself, especially work that explicitly tries to capture diversity in the set. Apart from work discussed earlier, recent work on diversity includes the use of determinantal point processes [140]. Work on off-policy correction for slate recommendations is relevant to learning models of user responses from data (e.g., [118,36]).…”

Section: Future Directions Extensions and Related Workmentioning

confidence: 99%

On the equivalence of optimal recommendation sets and myopically optimal query sets

Viappiani¹,

Boutilier

2020

Artificial Intelligence

View full text Add to dashboard Cite

Preference elicitation is an important component in many AI applications, including decision support and recommender systems. Such systems must assess user preferences, based on interactions with their users, and make recommendations using (possibly incomplete and imprecise) beliefs about those preferences. Mechanisms for explicit preference elicitation-asking users to answer direct queries about their preferences-can be of great value; but due to the cognitive and time cost imposed on users, it is important to minimize the number of queries by asking those that have high (expected) value of information. An alternative approach is to simply make recommendations and have users provide feedback (e.g., accept a recommendation or critique it in some way) and use this more indirect feedback to gradually improve the quality of the recommendations. Due to inherent uncertainty about a user's true preferences, often a set of recommendations is presented to the user at each stage. Conceptually, a set of recommendations can also be viewed as choice query, in which the user indicates which option is most preferred from that set. Because of the potential tension between making a good set recommendation and asking an informative choice query, we explore the connection between the two. We consider two different models of preference uncertainty and optimization: (a) a Bayesian framework in which a posterior over user utility functions is maintained, optimal recommendations are assessed using expected utility, and queries are assessed using expected value of information; and (b) a minimax-regret framework in which user utility uncertainty is strict (represented by a polytope), recommendations are made using the minimax-regret robustness criterion, and queries are assessed using worst-case regret reduction. We show that, somewhat surprisingly, in both cases, there is no tradeoff to be made between good recommendations and good queries: we prove that the optimal recommendation set of size k is also an optimal choice query of size k. We also examine the case where user responses to choice queries are error prone (using both constant and mixed multinomial logit noise models) showing the results are robust to this form of noise. In both frameworks, our theoretical results have practical consequences for the design of interactive recommenders. Our results also allow us to design efficient algorithms to compute optimal query/recommendation sets. We develop several such algorithms (both exact and approximate) for both settings and provide empirical validation of their performance.

show abstract

Section: Future Directions Extensions and Related Workmentioning

confidence: 99%

On the equivalence of optimal recommendation sets and myopically optimal query sets

Viappiani¹,

Boutilier

2020

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…From another perspective, (Cheng et al 2017) formulates the diversified recommendation problem as a supervised learning task, and proposes a diversified collaborative filtering model to solve the optimization problems. Recently, DPP has been demonstrated to be effective in modeling diversity in various machine learning problems (Kulesza, Taskar, and others 2012), and some recent work (Chen, Zhang, and Zhou 2018;Wilhelm et al 2018;Wu et al 2019a) employs DPP to improve recommendation diversity.…”

Section: Related Work Diversified Recommendationmentioning

confidence: 99%

Diversified Interactive Recommendation with Implicit Feedback

Liu

Xiao

et al. 2020

AAAI

View full text Add to dashboard Cite

Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attention. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsatisfying user experiences. In this paper, we propose a novel diversified recommendation model, named Diversified Contextual Combinatorial Bandit (DC2B), for interactive recommendation with users' implicit feedback. Specifically, DC2B employs determinantal point process in the recommendation procedure to promote diversity of the recommendation results. To learn the model parameters, a Thompson sampling-type algorithm based on variational Bayesian inference is proposed. In addition, theoretical regret analysis is also provided to guarantee the performance of DC2B. Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed method in balancing the recommendation accuracy and diversity.

show abstract

“…This method performs better than MMR in these fields. DPPs have been applied to recommendation problems as a way of taking diversity into account (Wilhelm et al, 2018;Chen et al, 2018;Mariet et al, 2019). Multi-document summarization models combine DPPs and neural networks to take account of diversity (Cho et al, 2019a;Cho et al, 2019b).…”

Section: Work On Diversitymentioning

confidence: 99%

“…From the definition of the determinant, the DPPs select important answers and do not select similar answers at the same time. Following Wilhelm et al (2018), the kernel matrix is decomposed into eigenvalues, and negative eigenvalues are replaced with tiny values to satisfy the semi-positive definiteness constraint. 1 In the training, the parameters of BERT are updated so that the following negative log-likelihood is minimized:…”

Section: Dppsmentioning

confidence: 99%

Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs

Fujita¹,

Shibata²,

Okumura³

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

In community-based question answering (CQA) platforms, it takes time for a user to get useful information from among many answers. Although one solution is an answer ranking method, the user still needs to read through the top-ranked answers carefully. This paper proposes a new task of selecting a diverse and non-redundant answer set rather than ranking the answers. Our method is based on determinantal point processes (DPPs), and it calculates the answer importance and similarity between answers by using BERT. We built a dataset focusing on a Japanese CQA site, and the experiments on this dataset demonstrated that the proposed method outperformed several baseline methods.

show abstract

Practical Diversified Recommendations on YouTube with Determinantal Point Processes

Cited by 108 publications

References 36 publications

On the equivalence of optimal recommendation sets and myopically optimal query sets

On the equivalence of optimal recommendation sets and myopically optimal query sets

Diversified Interactive Recommendation with Implicit Feedback

Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs

Contact Info

Product

Resources

About