Signed Distance-based Deep Memory Recommender

Tran, Thanh; Lee, Kyumin; Kong, Xiangnan

doi:10.1145/3308558.3313460

Cited by 16 publications

(27 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, several works [11,22] are proposed to weigh the missing data. In [14,36], metric learning is applied to compute the distance between users and items. With the ability to represent non-linear and complex data, (deep) neural networks have been utilized in the domain of recommendation and bring more opportunities to reshape the conventional recommendation architectures.…”

Section: Recommendation With Implicit Feedbackmentioning

confidence: 99%

Hierarchical Gating Networks for Sequential Recommendation

Peng

2019

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

215

119

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: Recommendation With Implicit Feedbackmentioning

confidence: 99%

Hierarchical Gating Networks for Sequential Recommendation

Peng

2019

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

215

119

View full text Add to dashboard Cite

show abstract

“…retrieval or nomination) stage aims to provide a small set of related items from a large corpus under stringent latency requirements [6,35]. Then, the candidate ranking model reranks the retrieved items based on click-through rate (CTR for short), rating or score [10,30,34]. In the retrieval stage, recommenders have to face the computational barriers of full corpus retrieval.…”

Section: Candidate Generation and Rankingmentioning

confidence: 99%

“…Many recent neural recommenders utilize attention mechanism to lter diverse user interests by concentrating on relevant behaviors and eliminating irrelevant ones to predict a user's future action [10,20,23,30,36,39]. Among these attentive neural recommenders, researches [10,20] assign weights to compressed hidden states to build attentive RNN models; researches [23,30] assign weights to historical records to build attentive memory networks; and researches [36,39] assign weights to hidden variables to build deep attentive feed-forward networks. But when calculating the correlation between two behaviors, the time interval between them has not been taken into consideration by most of the previous approaches.…”

Section: Introductionmentioning

confidence: 99%

Sequential Recommender via Time-aware Attentive Memory Network

Wang²,

Wang

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recommendation systems aim to assist users to discover most preferred contents from an ever-growing corpus of items. Although recommenders have been greatly improved by deep learning, they still face several challenges: (1) Behaviors are much more complex than words in sentences, so traditional attentive and recurrent models have limitations capturing the temporal dynamics of user preferences. (2) The preferences of users are multiple and evolving, so it is di cult to integrate long-term memory and short-term intent. In this paper, we propose a temporal gating methodology to improve attention mechanism and recurrent units, so that temporal information can be considered in both information ltering and state transition. Additionally, we propose a hybrid sequential recommender, named Multi-hop Time-aware Attentive Memory network (MTAM), to integrate long-term and short-term preferences. We use the proposed time-aware GRU network to learn the short-term intent and maintain prior records in user memory. We treat the short-term intent as a query and design a multi-hop memory reading operation via the proposed time-aware attention to generate user representation based on the current intent and longterm memory. Our approach is scalable for candidate retrieval tasks and can be viewed as a non-linear generalization of latent factorization for dot-product based Top-K recommendation. Finally, we conduct extensive experiments on six benchmark datasets and the experimental results demonstrate the e ectiveness of our MTAM and temporal gating methodology.

show abstract

“…In other cases, temporal data is utilized to predict the next item based on recent activity. For example, Distance Based Memory Recommender (SDMR) [37] is not a sequential model, but it does utilize recent activities as contextual side-information. The contribution and the focus of this work is different from these models, as AMP-CF does not utilize any temporal information.…”

Section: Related Workmentioning

confidence: 99%

Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering

Barkan

Fuchs

Caciularu

et al. 2020

Fourteenth ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Two main challenges in recommender systems are modeling users with heterogeneous taste, and providing explainable recommendations. In this paper, we propose the neural Attentive Multi-Persona Collaborative Filtering (AMP-CF) model as a unified solution for both problems. AMP-CF breaks down the user to several latent 'personas' (profiles) that identify and discern the different tastes and inclinations of the user. Then, the revealed personas are used to generate and explain the final recommendation list for the user. AMP-CF models users as an attentive mixture of personas, enabling a dynamic user representation that changes based on the item under consideration. We demonstrate AMP-CF on five collaborative filtering datasets from the domains of movies, music, video games and social networks. As an additional contribution, we propose a novel evaluation scheme for comparing the different items in a recommendation list based on the distance from the underlying distribution of "tastes" in the user's historical items. Experimental results show that AMP-CF is competitive with other state-of-the-art models. Finally, we provide qualitative results to showcase the ability of AMP-CF to explain its recommendations. CCS Concepts: • Computing methodologies → Learning latent representations; • Information systems → Collaborative filtering.

show abstract

Signed Distance-based Deep Memory Recommender

Cited by 16 publications

References 53 publications

Hierarchical Gating Networks for Sequential Recommendation

Hierarchical Gating Networks for Sequential Recommendation

Sequential Recommender via Time-aware Attentive Memory Network

Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering

Contact Info

Product

Resources

About