Item recommendation on monotonic behavior chains

Wan, Mengting; McAuley, Julian

doi:10.1145/3240323.3240369

Cited by 198 publications

(136 citation statements)

References 17 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…The proposed model is evaluated on five real-world datasets from various domains with different sparsities: MovieLens-20M [6], Amazon-Books and Amazon-CDs [9], Goodreads-Children and Goodreads-Comics [38]. MovieLens-20M is a user-movie dataset collected from the MovieLens website, where this dataset has 20 million usermovie interactions.…”

Section: Datasetsmentioning

confidence: 99%

Hierarchical Gating Networks for Sequential Recommendation

Peng

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

249

121

View full text Add to dashboard Cite

The chronological order of user-item interactions is a key feature in many recommender systems, where the items that users will interact may largely depend on those items that users just accessed recently. However, with the tremendous increase of users and items, sequential recommender systems still face several challenging problems: (1) the hardness of modeling the long-term user interests from sparse implicit feedback; (2) the difficulty of capturing the shortterm user interests given several items the user just accessed. To cope with these challenges, we propose a hierarchical gating network (HGN), integrated with the Bayesian Personalized Ranking (BPR) to capture both the long-term and short-term user interests. Our HGN consists of a feature gating module, an instance gating module, and an item-item product module. In particular, our feature gating and instance gating modules select what item features can be passed to the downstream layers from the feature and instance levels, respectively. Our item-item product module explicitly captures the item relations between the items that users accessed in the past and those items users will access in the future. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on five real-world datasets. The experimental results demonstrate the effectiveness of our model on Top-N sequential recommendation. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Datasetsmentioning

confidence: 99%

Hierarchical Gating Networks for Sequential Recommendation

Peng

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

249

121

View full text Add to dashboard Cite

show abstract

“…7 A recently introduced large dataset containing book metadata and user actions (e.g. shelve, read, rate) [39]. We treat the most abundant action ('shelve') as implicit feedback.…”

Section: Datasetsmentioning

confidence: 99%

“…We treat the most abundant action ('shelve') as implicit feedback. As shown in [39], the dataset is dominated by a few popular items (e.g. over 1/3 of users added Harry Potter #1 to their shelves), such that always recommending the most popular books achieves high Top-N accuracy; we ignore such outliers by discarding the 0.1% of most popular books.…”

Section: Datasetsmentioning

confidence: 99%

Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation

Kang

McAuley

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Generating the Top-N recommendations from a large corpus is computationally expensive to perform at scale. Candidate generation and re-ranking based approaches are often adopted in industrial settings to alleviate efficiency problems. However it remains to be fully studied how well such schemes approximate complete rankings (or how many candidates are required to achieve a good approximation), or to develop systematic approaches to generate high-quality candidates efficiently. In this paper, we seek to investigate these questions via proposing a candidate generation and re-ranking based framework (CIGAR), which first learns a preference-preserving binary embedding for building a hash table to retrieve candidates, and then learns to re-rank the candidates using real-valued ranking models with a candidate-oriented objective. We perform a comprehensive study on several large-scale real-world datasets consisting of millions of users/items and hundreds of millions of interactions. Our results show that CIGAR significantly boosts the Top-N accuracy against state-of-the-art recommendation models, while reducing the query time by orders of magnitude. We hope that this work could draw more attention to the candidate generation problem in recommender systems.

show abstract

“…In contrast, implicit feedback is much easier to collect although it is less accurate in reflecting the user preferences, as there is no explicit judgement by the users as to their liking of the item [17]. The difference between explicit and implicit feedback has led researchers to develop different models and techniques to address each of their distinct properties [23]. Multiple types of explicit and implicit feedback may be available in real-world recommendation systems and could potentially complement each other.…”

Section: Introductionmentioning

confidence: 99%

“…Models of rating prediction leverage only the subset of user-item interactions where a rating is observed while the ranking models leverage all user-item interactions whether the user deliberately chose to assign a rating value or not. The users of a real-world recommendation system follow 'monotonic behaviour chains' [23], i.e. the user behaviour is represented as a chain of implicit feedback (e.g.…”

Section: Introductionmentioning

confidence: 99%

Unifying Explicit and Implicit Feedback for Rating Prediction and Ranking Recommendation Tasks

Jadidinejad

Macdonald

Ounis

2019

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval

View full text Add to dashboard Cite

The two main tasks addressed by collaborative filtering approaches are rating prediction and ranking. Rating prediction models leverage explicit feedback (e.g. ratings), and aim to estimate the rating a user would assign to an unseen item. In contrast, ranking models leverage implicit feedback (e.g. clicks) in order to provide the user with a personalized ranked list of recommended items. Several previous approaches have been proposed that learn from both explicit and implicit feedback to optimize the task of ranking or rating prediction at the level of recommendation algorithm. Yet we argue that these two tasks are not completely separate, but are part of a unified process: a user first interacts with a set of items and then might decide to provide explicit feedback on a subset of items. We propose to bridge the gap between the tasks of rating prediction and ranking through the use of a novel weak supervision approach that unifies both explicit and implicit feedback datasets. The key aspects of the proposed model is that (1) it is applied at the level of data pre-processing and (2) it increases the representation of less popular items in recommendations while maintaining reasonable recommendation performance. Our experimental results -on six datasets covering different types of heterogeneous user's interactions and using a wide range of evaluation metrics -show that, our proposed approach can effectively combine explicit and implicit feedback and improve the effectiveness of the baseline explicit model on the ranking task by covering a broader range of long-tail items.

show abstract

Item recommendation on monotonic behavior chains

Cited by 198 publications

References 17 publications

Hierarchical Gating Networks for Sequential Recommendation

Hierarchical Gating Networks for Sequential Recommendation

Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation

Unifying Explicit and Implicit Feedback for Rating Prediction and Ranking Recommendation Tasks

Contact Info

Product

Resources

About