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

Kang, Wang-Cheng; McAuley, Julian

doi:10.1145/3357384.3357930

Cited by 49 publications

(45 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, merely adopting the list-wise loss can have adverse effects on the ranking performance. Because a user is interested in only a few items among the numerous total items [10], learning the detailed ranking orders of all the unobserved items is not only daunting but also ineffective. The recommendation list from the teacher model contains information about a user's potential preference on each unobserved item; A few items that the user would be interested in (i.e., interesting items) are located near the top of the list, whereas the majority of items that the user would not be interested in (i.e., uninteresting items) are located far from the top.…”

Section: Relaxed Ranking Distillation (Rrd)mentioning

confidence: 99%

DE-RRD: A Knowledge Distillation Framework for Recommender System

Kang

Hwang

Kweon

et al. 2020

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

View full text Add to dashboard Cite

Recent recommender systems have started to employ knowledge distillation, which is a model compression technique distilling knowledge from a cumbersome model (teacher) to a compact model (student), to reduce inference latency while maintaining performance. The state-of-the-art methods have only focused on making the student model to accurately imitate the predictions of the teacher model. They have a limitation in that the prediction results incompletely reveal the teacher's knowledge. In this paper, we propose a novel knowledge distillation framework for recommender system, called DE-RRD, which enables the student model to learn from the latent knowledge encoded in the teacher model as well as from the teacher's predictions. Concretely, DE-RRD consists of two methods: 1) Distillation Experts (DE) that directly transfers the latent knowledge from the teacher model. DE exploits "experts" and a novel expert selection strategy for effectively distilling the vast teacher's knowledge to the student with limited capacity. 2) Relaxed Ranking Distillation (RRD) that transfers the knowledge revealed from the teacher's prediction with consideration of the relaxed ranking orders among items. Our extensive experiments show that DE-RRD outperforms the state-of-the-art competitors and achieves comparable or even better performance to that of the teacher model with faster inference time. CCS CONCEPTS • Information systems → Learning to rank; Collaborative filtering; Retrieval efficiency.

show abstract

Section: Relaxed Ranking Distillation (Rrd)mentioning

confidence: 99%

DE-RRD: A Knowledge Distillation Framework for Recommender System

Kang

Hwang

Kweon

et al. 2020

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

View full text Add to dashboard Cite

show abstract

“…To prove the validity of the model and the better performance on the test set, the dimensions of the user and item representations in all methods are set to the same factors and all parameters are tuned. On Amazon datasets, the regularized tuning parameter is 20 in most cases, and BPR-MF [35], FPMC [36], VBPR [18], and CIGAR [37] perform best on area under curve (AUC). For each data set, we report the average AUC (representing all commodities) on the complete test set T and the subset of T, which contains only items with less than 5 positive feedback instances.…”

Section: Evaluation Methods and Discussionmentioning

confidence: 99%

Learning Context-Aware Outfit Recommendation

2020

View full text Add to dashboard Cite

With the rapid development and increasing popularity of online shopping for fashion products, fashion recommendation plays an important role in daily online shopping scenes. Fashion is not only a commodity that is bought and sold but is also a visual language of sign, a nonverbal communication medium that exists between the wearers and viewers in a community. The key to fashion recommendation is to capture the semantics behind customers’ fit feedback as well as fashion visual style. Existing methods have been developed with the item similarity demonstrated by user interactions like ratings and purchases. By identifying user interests, it is efficient to deliver marketing messages to the right customers. Since the style of clothing contains rich visual information such as color and shape, and the shape has symmetrical structure and asymmetrical structure, and users with different backgrounds have different feelings on clothes, therefore affecting their way of dress. In this paper, we propose a new method to model user preference jointly with user review information and image region-level features to make more accurate recommendations. Specifically, the proposed method is based on scene images to learn the compatibility from fashion or interior design images. Extensive experiments have been conducted on several large-scale real-world datasets consisting of millions of users/items and hundreds of millions of interactions. Extensive experiments indicate that the proposed method effectively improves the performance of items prediction as well as of outfits matching.

show abstract

“…As majority of items are irrelevant to the users, the two aforementioned steps are usually employed to achieve high efficiency in personalized recommendation (Covington et al, 2016;Kang & McAuley, 2019). On one hand, the candidate generation component relies on heuristics or retrievalefficient structures to recall a small subset of relevant items, to reduce the number of similarity evaluations in the ranking step (Guo et al, 2020).…”

Section: Candidate Generationmentioning

confidence: 99%

Efficient Retrieval of Matrix Factorization-Based Top-k Recommendations: A Survey of Recent Approaches

Le¹,

Lauw²

2021

jair

View full text Add to dashboard Cite

Top-k recommendation seeks to deliver a personalized list of k items to each individual user. An established methodology in the literature based on matrix factorization (MF), which usually represents users and items as vectors in low-dimensional space, is an effective approach to recommender systems, thanks to its superior performance in terms of recommendation quality and scalability. A typical matrix factorization recommender system has two main phases: preference elicitation and recommendation retrieval. The former analyzes user-generated data to learn user preferences and item characteristics in the form of latent feature vectors, whereas the latter ranks the candidate items based on the learnt vectors and returns the top-k items from the ranked list. For preference elicitation, there have been numerous works to build accurate MF-based recommendation algorithms that can learn from large datasets. However, for the recommendation retrieval phase, naively scanning a large number of items to identify the few most relevant ones may inhibit truly real-time applications. In this work, we survey recent advances and state-of-the-art approaches in the literature that enable fast and accurate retrieval for MF-based personalized recommendations. Also, we include analytical discussions of approaches along different dimensions to provide the readers with a more comprehensive understanding of the surveyed works.

show abstract

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

Cited by 49 publications

References 42 publications

DE-RRD: A Knowledge Distillation Framework for Recommender System

DE-RRD: A Knowledge Distillation Framework for Recommender System

Learning Context-Aware Outfit Recommendation

Efficient Retrieval of Matrix Factorization-Based Top-k Recommendations: A Survey of Recent Approaches

Contact Info

Product

Resources

About