Compositional Coding for Collaborative Filtering

Liu, Chenghao; Lu, Tao; Xin, Wang; Cheng, Zhiyong; Sun, Jun; Hoi, Steven C. H.

doi:10.1145/3331184.3331206

Cited by 15 publications

(19 citation statements)

References 32 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Wang et al, 2019) exploits graph convolutional network (GCN) to model high-order feature from implicit feedback and distill the ranking information derived from GCN to binarized collaborative filtering to improve the efficiency of online recommendation. (Liu et al, 2019a) introduces a new approach Compositional Coding for Collaborative Filtering (CCCF) that represents each user/item with a set of binary vectors, instead of one as in (Zhang et al, 2016), which are associated with a set of sparse real-value weight vectors. CCCF claims to achieve better recommendation efficiency than many other discrete learning methods.…”

Section: Optimization-based Discretizationmentioning

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

Section: Optimization-based Discretizationmentioning

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

show abstract

“…To reduce the time complexity, an approximate nearest neighbor search based on the Hdidx library is used to index extracted image features and save them in the retrieval engine. This can reduce the search time by converting the image features on the high-dimensional space using the Hdidx library into compact binary codes [30][31][32].…”

Section: Image-based Similar Product Retrieval Modelmentioning

confidence: 99%

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning

Lee

et al. 2020

Electronics

View full text Add to dashboard Cite

The digitization of the fashion industry diversified consumer segments, and consumers now have broader choices with shorter production cycles; digital technology in the fashion industry is attracting the attention of consumers. Therefore, a system that efficiently supports the searching and recommendation of a product is becoming increasingly important. However, the text-based search method has limitations because of the nature of the fashion industry, in which design is a very important factor. Therefore, we developed an intelligent fashion technique based on deep learning for efficient fashion product searches and recommendations consisting of a Sketch-Product fashion retrieval model and vector-based user preference fashion recommendation model. It was found that the “Precision at 5” of the image-based similar product retrieval model was 0.774 and that of the sketch-based similar product retrieval model was 0.445. The vector-based preference fashion recommendation model also showed positive performance. This system is expected to enhance consumers’ satisfaction by supporting users in more effectively searching for fashion products or by recommending fashion products before they begin a search.

show abstract

“…For efficiency reasons, a number of hashing-based approaches have also been proposed for the recommendation domain. These approaches have primarily focused on the collaborative filtering setting [39,45,65,68,71], but less so on content-aware approaches addressing the cold-start problem. Existing content-aware hashing approaches, DDL [67] and DCMF [42], learn to generate user and item hash codes for use in both standard and cold-start settings, however they both share the problem of generating item hash codes differently depending on whether the item is considered cold-start or not.…”

Section: Chapter 5 Content-aware Neural Hashing For Cold-start Recomm...mentioning

confidence: 99%

“…For example, in a collaborative filtering setting the user hash code represents the query, and depending on the user's historic item interactions, it may be possible to infer that certain underlying properties are more important for the item ranking. While approaches have been proposed for assigning real-valued weights to certain substrings of bits in a hash code [14,45], such a weighting has the problem of making the core similarity computation (e.g., Hamming distance) significantly slower, which limits its usage in large-scale settings where hashing-based solutions are most needed. This leads to the next research question:…”

Section: Chapter 6 Projected Hamming Dissimilarity For Bit-level Impo...mentioning

confidence: 99%

Unsupervised Neural Generative Semantic Hashing

Hansen

Simonsen

et al. 2019

Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been obtained through neural network based models: generative models trained by learning to reconstruct the original documents. We present a novel unsupervised generative semantic hashing approach, Ranking based Semantic Hashing (RBSH) that consists of both a variational and a ranking based component. Similarly to variational autoencoders, the variational component is trained to reconstruct the original document conditioned on its generated hash code, and as in prior work, it only considers documents individually. The ranking component solves this limitation by incorporating inter-document similarity into the hash code generation, modelling document ranking through a hinge loss. To circumvent the need for labelled data to compute the hinge loss, we use a weak labeller and thus keep the approach fully unsupervised.Extensive experimental evaluation on four publicly available datasets against traditional baselines and recent state-of-the-art methods for semantic hashing shows that RBSH significantly outperforms all other methods across all evaluated hash code lengths. In fact, RBSH hash codes are able to perform similarly to state-ofthe-art hash codes while using 2-4x fewer bits.

show abstract

Compositional Coding for Collaborative Filtering

Cited by 15 publications

References 32 publications

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

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

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning

Unsupervised Neural Generative Semantic Hashing

Contact Info

Product

Resources

About