short-paper

GLocal-K: Global and Local Kernels for Recommender Systems

Authors:

Soyeon Caren Han,

Taejun Lim,

Siqu Long,

Bernd Burgstaller, and

Josiah PoonAuthors Info & Claims

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

October 2021

Pages 3063 - 3067

https://doi.org/10.1145/3459637.3482112

Published: 30 October 2021 Publication History

Get Access

Abstract

Recommender systems typically operate on high-dimensional sparse user-item matrices. Matrix completion is a very challenging task to predict one's interest based on millions of other users having each seen a small subset of thousands of items. We propose a G lobal-Local Kernel-based matrix completion framework, named GLocal-K, that aims to generalise and represent a high-dimensional sparse user-item matrix entry into a low dimensional space with a small number of important features. Our GLocal-K can be divided into two major stages. First, we pre-train an auto encoder with the local kernelised weight matrix, which transforms the data from one space into the feature space by using a 2d-RBF kernel. Then, the pre-trained auto encoder is fine-tuned with the rating matrix, produced by a convolution-based global kernel, which captures the characteristics of each item. We apply our GLocal-K model under the extreme low-resource setting, which includes only a user-item rating matrix, with no side information. Our model outperforms the state-of-the-art baselines on three collaborative filtering benchmarks: ML-100K, ML-1M, and Douban.

Supplementary Material

MP4 File (CIKM2021.mp4)

Recent studies focused on utilising side information, such as opinion information or attributes of users. However, in most real-world settings (e.g., platforms and websites), there is no (or insufficient) side information available about users. Instead of considering side information, we focus on improving the feature extraction performance for a high-dimensional user-item rating matrix into a low-dimensional latent feature space. We propose a Global Local Kernel-based matrix completion framework, named GLocal-K, that aims to generalise and represent a high-dimensional sparse user-item matrix entry into a low dimensional space with a small number of important features. It uses two types of kernels in two stages respectively: pre-training (with the local kernelised weight matrix) and fine-tuning (with the global-kernel based matrix). It is hoped that our Global-K gives some insight into the future integration of both kernels for high-dimensional sparse matrix completion with no side information.

Download
101.08 MB

References

[1]

Rianne van den Berg, Thomas N Kipf, and Max Welling. 2018. Graph convolutional matrix completion. KDD Deep Learning Day (2018).

Google Scholar

[2]

Emmanuel J Candès and Benjamin Recht. 2009. Exact matrix completion via convex optimization. Foundations of Computational mathematics, Vol. 9, 6 (2009), 717--772.

Google Scholar

[3]

Theodoros Giannakopoulos, Aggelos Pikrakis, and Sergios Theodoridis. 2008. A novel efficient approach for audio segmentation. In 2008 19th International Conference on Pattern Recognition. IEEE, 1--4.

Crossref

Google Scholar

[4]

Joonseok Lee, Seungyeon Kim, Guy Lebanon, Yoram Singer, and Samy Bengio. 2016. LLORMA: Local Low-Rank Matrix Approximation. Journal of Machine Learning Research, Vol. 17, 15 (2016), 1--24.

Digital Library

Google Scholar

[5]

Federico Monti, Michael M Bronstein, and Xavier Bresson. 2017. Geometric matrix completion with recurrent multi-graph neural networks. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 3700--3710.

Digital Library

Google Scholar

[6]

Lorenz Muller, Julien Martel, and Giacomo Indiveri. 2018. Kernelized synaptic weight matrices. In International Conference on Machine Learning. PMLR, 3654--3663.

Google Scholar

[7]

Ahmed Rashed, Josif Grabocka, and Lars Schmidt-Thieme. 2019. Attribute-aware non-linear co-embeddings of graph features. In Proceedings of the 13th ACM Conference on Recommender Systems. 314--321.

Digital Library

Google Scholar

[8]

Suvash Sedhain, Aditya Krishna Menon, Scott Sanner, and Lexing Xie. 2015. Autorec: Autoencoders meet collaborative filtering. In Proceedings of the 24th international conference on World Wide Web. 111--112.

Digital Library

Google Scholar

[9]

Jonathan Strahl, Jaakko Peltonen, Hirsohi Mamitsuka, and Samuel Kaski. 2020. Scalable probabilistic matrix factorization with graph-based priors. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 5851--5858.

Crossref

Google Scholar

[10]

A Ugla, Dhuha J Kamil, Hassan J Khaudair, et al. 2020. Interpretable Recommender System With Heterogeneous Information: A Geometric Deep Learning Perspective. International Journal of Mechanical and Production Engineering Research and Development (IJMPERD), Vol. 10, 3 (2020), 2411--2430.

Google Scholar

[11]

Guijuan Zhang, Yang Liu, and Xiaoning Jin. 2020. A survey of autoencoder-based recommender systems. Frontiers of Computer Science, Vol. 14, 2 (2020), 430--450.

Digital Library

Google Scholar

[12]

Muhan Zhang and Yixin Chen. 2020. Inductive Matrix Completion Based on Graph Neural Networks. In International Conference on Learning Representations.

Google Scholar

[13]

Yin Zheng, Bangsheng Tang, Wenkui Ding, and Hanning Zhou. 2016. A neural autoregressive approach to collaborative filtering. In International Conference on Machine Learning. PMLR, 764--773.

Digital Library

Google Scholar

Cited By

View all

Costa JMarinho LSantos RParra D(2023)Evaluating Pre-training Strategies for Collaborative FilteringProceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization10.1145/3565472.3592949(175-182)Online publication date: 18-Jun-2023
https://dl.acm.org/doi/10.1145/3565472.3592949
Henriques RPinto L(2023)A novel evaluation framework for recommender systems in big data environmentsExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.120659231:COnline publication date: 30-Nov-2023
https://dl.acm.org/doi/10.1016/j.eswa.2023.120659
Yang DNgoc KShin IHwang M(2023)DPReLU: Dynamic Parametric Rectified Linear Unit and Its Proper Weight Initialization MethodInternational Journal of Computational Intelligence Systems10.1007/s44196-023-00186-w16:1Online publication date: 11-Feb-2023
https://doi.org/10.1007/s44196-023-00186-w
Show More Cited By

Index Terms

GLocal-K: Global and Local Kernels for Recommender Systems
1. Information systems
  1. Information retrieval
    1. Retrieval tasks and goals
      1. Recommender systems
2. Theory of computation
  1. Theory and algorithms for application domains
    1. Machine learning theory
      1. Kernel methods

Recommendations

Adaptive matrix completion for the users and the items in tail
WWW '19: The World Wide Web Conference

Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering ...
Read More
Boolean kernels for collaborative filtering in top-N item recommendation

In many personalized recommendation problems available data consists only of positive interactions (implicit feedback) between users and items. This problem is also known as One-Class Collaborative Filtering (OC-CF). Linear models usually achieve state-...
Read More
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data Mining

Recommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
Read More

Comments

Information & Contributors

Information

Published In

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

October 2021

4966 pages

ISBN:9781450384469

DOI:10.1145/3459637

General Chairs:
Gianluca Demartini
The University of Queensland, Australia
,
Guido Zuccon
The University of Queensland, Australia
,
Program Chairs:
J. Shane Culpepper
RMIT University, Australia
,
Zi Huang
The University of Queensland, Australia
,
Hanghang Tong
University of Illinois at Urbana-Champaign, USA

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Conference

CIKM '21

Sponsor:

CIKM '21: The 30th ACM International Conference on Information and Knowledge Management

November 1 - 5, 2021

Queensland, Virtual Event, Australia

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
254
Total Downloads

Downloads (Last 12 months)67
Downloads (Last 6 weeks)5

Other Metrics

View Author Metrics

Citations

Cited By

View all

Costa JMarinho LSantos RParra D(2023)Evaluating Pre-training Strategies for Collaborative FilteringProceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization10.1145/3565472.3592949(175-182)Online publication date: 18-Jun-2023
https://dl.acm.org/doi/10.1145/3565472.3592949
Henriques RPinto L(2023)A novel evaluation framework for recommender systems in big data environmentsExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.120659231:COnline publication date: 30-Nov-2023
https://dl.acm.org/doi/10.1016/j.eswa.2023.120659
Yang DNgoc KShin IHwang M(2023)DPReLU: Dynamic Parametric Rectified Linear Unit and Its Proper Weight Initialization MethodInternational Journal of Computational Intelligence Systems10.1007/s44196-023-00186-w16:1Online publication date: 11-Feb-2023
https://doi.org/10.1007/s44196-023-00186-w
Ganguli DHernandez DLovitt LAskell ABai YChen AConerly TDassarma NDrain DElhage NEl Showk SFort SHatfield-Dodds ZHenighan TJohnston SJones AJoseph NKernian JKravec SMann BNanda NNdousse KOlsson CAmodei DBrown TKaplan JMcCandlish SOlah CAmodei DClark J(2022)Predictability and Surprise in Large Generative ModelsProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency10.1145/3531146.3533229(1747-1764)Online publication date: 21-Jun-2022
https://dl.acm.org/doi/10.1145/3531146.3533229
Bourhim SBenhiba LIdrissi M(2022)A Community-Driven Deep Collaborative Approach for Recommender SystemsIEEE Access10.1109/ACCESS.2022.323032310(131144-131152)Online publication date: 2022
https://doi.org/10.1109/ACCESS.2022.3230323

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Adaptive matrix completion for the users and the items in tail

Boolean kernels for collaborative filtering in top-N item recommendation

A Scalable, Accurate Hybrid Recommender System