In sequential recommender system applications, it is important to develop models that can capture users’ evolving interest over time to successfully recommend future items that
they are likely to interact with. For users with long histories,
typical models based on recurrent neural networks tend to
forget important items in the distant past. Recent works have
shown that storing a small sketch of past items can improve
sequential recommendation tasks. However, these works all
rely on static sketching policies, i.e., heuristics to select items
to keep in the sketch, which are not necessarily optimal and
cannot improve over time with more training data. In this paper, we propose a differentiable policy for sketching (DiPS),
a framework that learns a data-driven sketching policy in an
end-to-end manner together with the recommender system
model to explicitly maximize recommendation quality in the
future. We also propose an approximate estimator of the gradient for optimizing the sketching algorithm parameters that is
computationally efficient. We verify the effectiveness of DiPS
on real-world datasets under various practical settings and
show that it requires up to 50% fewer sketch items to reach
the same predictive quality than existing sketching policies.
more »
« less
DiPS: Differentiable Policy for Sketching in Recommender Systems
In sequential recommender system applications, it is important to develop models that can capture users' evolving interest over time to successfully recommend future items that they are likely to interact with. For users with long histories, typical models based on recurrent neural networks tend to forget important items in the distant past. Recent works have shown that storing a small sketch of past items can improve sequential recommendation tasks. However, these works all rely on static sketching policies, i.e., heuristics to select items to keep in the sketch, which are not necessarily optimal and cannot improve over time with more training data. In this paper, we propose a differentiable policy for sketching (DiPS), a framework that learns a data-driven sketching policy in an end-to-end manner together with the recommender system model to explicitly maximize recommendation quality in the future. We also propose an approximate estimator of the gradient for optimizing the sketching algorithm parameters that is computationally efficient. We verify the effectiveness of DiPS on real-world datasets under various practical settings and show that it requires up to 50% fewer sketch items to reach the same predictive quality than existing sketching policies.
more »
« less
- Award ID(s):
- 1917713
- NSF-PAR ID:
- 10339505
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 36
- Issue:
- 6
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 6703 to 6712
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Sequential recommendation is the task of predicting the next items for users based on their interaction history. Modeling the dependence of the next action on the past actions accurately is crucial to this problem. Moreover, sequential recommendation often faces serious sparsity of item-to-item transitions in a user's action sequence, which limits the practical utility of such solutions. To tackle these challenges, we propose a Category-aware Collaborative Sequential Recommender. Our preliminary statistical tests demonstrate that the in-category item-to-item transitions are often much stronger indicators of the next items than the general item-to-item transitions observed in the original sequence. Our method makes use of item category in two ways. First, the recommender utilizes item category to organize a user's own actions to enhance dependency modeling based on her own past actions. It utilizes self-attention to capture in-category transition patterns, and determines which of the in-category transition patterns to consider based on the categories of recent actions. Second, the recommender utilizes the item category to retrieve users with similar in-category preferences to enhance collaborative learning across users, and thus conquer sparsity. It utilizes attention to incorporate in-category transition patterns from the retrieved users for the target user. Extensive experiments on two large datasets prove the effectiveness of our solution against an extensive list of state-of-the-art sequential recommendation models.more » « less
-
Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system’s ease of use, and gain users’ trust. A typical approach to realize it is natural language generation. However, previous works mostly adopt recurrent neural networks to meet the ends, leaving the potentially more effective pre-trained Transformer models under-explored. In fact, user and item IDs, as important identifiers in recommender systems, are inherently in different semantic space as words that pre-trained models were already trained on. Thus, how to effectively fuse IDs into such models becomes a critical issue. Inspired by recent advancement in prompt learning, we come up with two solutions: find alternative words to represent IDs (called discrete prompt learning) and directly input ID vectors to a pre-trained model (termed continuous prompt learning). In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages. To bridge the gap, we further propose two training strategies: sequential tuning and recommendation as regularization. Extensive experiments show that our continuous prompt learning approach equipped with the training strategies consistently outperforms strong baselines on three datasets of explainable recommendation.more » « less
-
null (Ed.)The success of cross-domain recommender systems in capturing user interests across multiple domains has recently brought much attention to them. These recommender systems aim to improve the quality of suggestions and defy the cold-start problem by transferring information from one (or more) source domain(s) to a target domain. However, most cross-domain recommenders ignore the sequential information in user history. They only rely on an aggregate or snapshot of user feedback in the past. Most importantly, they do not explicitly model how users transition from one domain to another domain as users continue to interact with different item domains. In this paper, we argue that between-domain transitions in user sequences are useful in improving recommendation quality, dealing with the cold-start problem, and revealing interesting aspects of how user interests transform from one domain to another. We propose TransCrossCF, transition-based cross-domain collaborative filtering, that can capture both within and between domain transitions of user feedback sequences while understanding the relationship between different item types in different domains. Specifically, we model each purchase of a user as a transition from his/her previous item to the next one, under the effect of item domains and user preferences. Our intensive experiments demonstrate that TransCrossCF outperforms the state-of-the-art methods in recommendation task on three real-world datasets, both in the cold-start and hot-start scenarios. Moreover, according to our context analysis evaluations, the between-domain relations captured by TransCrossCF are interpretable and intuitive.more » « less
-
null (Ed.)Recommender systems learn from past user preferences in order to predict future user interests and provide users with personalized suggestions. Previous research has demonstrated that biases in user profiles in the aggregate can influence the recommendations to users who do not share the majority preference. One consequence of this bias propagation effect is miscalibration, a mismatch between the types or categories of items that a user prefers and the items provided in recommendations. In this paper, we conduct a systematic analysis aimed at identifying key characteristics in user profiles that might lead to miscalibrated recommendations. We consider several categories of profile characteristics, including similarity to the average user, propensity towards popularity, profile diversity, and preference intensity. We develop predictive models of miscalibration and use these models to identify the most important features correlated with miscalibration, given different algorithms and dataset characteristics. Our analysis is intended to help system designers predict miscalibration effects and to develop recommendation algorithms with improved calibration properties.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1609/aaai.v36i6.20625
