A Survey on Stream-Based Recommender Systems

Al-Ghossein, Marie; Abdessalem, Talel; Barré, Anthony

doi:10.1145/3453443

Cited by 23 publications

(11 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, the timestamp labeled on each interaction should indicate the actual time when the interaction happened, i.e., the time when user watches the movie , not the time when user give likes or dislikes feedback on movie . Despite the fact that some of such datasets have been utilized in IURS, some researchers [4] doubt that they are actually not suitable for the particular problem of IURS.…”

Section: Datasetsmentioning

confidence: 99%

A Survey on Incremental Update for Neural Recommender Systems

Zhang¹,

Kim²

2023

Preprint

View full text Add to dashboard Cite

Recommender Systems (RS) aim to provide personalized suggestions of items for users against consumer over-choice. Although extensive research has been conducted to address different aspects and challenges of RS, there still exists a gap between academic research and industrial applications. Specifically, most of the existing models still work in an offline manner, in which the recommender is trained on a large static training set and evaluated on a very restrictive testing set in a one-time process. RS will stay unchanged until next batch retrain is performed. We frame such RS as Batch Update Recommender Systems (BURS). In reality, they have to face the challenges where RS are expected to be instantly updated with new data streaming in, and generate updated recommendations for current user activities based on the newly arrived data. We frame such RS as Incremental Update Recommender Systems (IURS).In this article, we offer a systematic survey of incremental update for neural recommender systems. We begin the survey by introducing key concepts and formulating the task of IURS. We then illustrate the challenges in IURS compared with traditional BURS. Afterwards, we detail the introduction of existing literature and evluation issues. We conclude the survey by outlining some prominent open research issues in this area.

show abstract

Section: Datasetsmentioning

confidence: 99%

A Survey on Incremental Update for Neural Recommender Systems

Zhang¹,

Kim²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the third case, the model constantly learns from a continuous stream of interactions. Such approaches, known as stream-based recommender systems [6], [9], require the greatest engineering effort. Even in the case of collaborative filtering, these methods are able to recommend an item after some user has interacted with it [10].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Real-Time and Batch Job Recommendations

Kwiecinski

Melniczak²,

Górecki

2023

IEEE Access

View full text Add to dashboard Cite

Collaborative filtering recommendation systems are traditionally trained in a batch manner and are designed to produce personalized recommendations for a large number of users at the same time. However, in many industrial use cases, it is reasonable to produce recommendations in real time, taking account of very recent user interactions. In this work, we present the implementation of batch and real-time recommendation systems using the example of the RP3Beta model, a simple scalable graph-based model that outperforms multiple more advanced models. Our approach can be utilized by any recommendation system if user-to-item recommendations can be obtained based on item-to-item recommendations. We show that it covers multiple common recommendation models, especially collaborative filtering approaches where user features are not available. We also provide the results of A/B tests comparing these two approaches in a real-world scenario of a job recommendation task, conducted with almost 200,000 OLX users. We report at least 10% more users applying for recommended job ads when using a real-time instead of a batch approach. We believe that our results can help other organizations to take informed decisions about whether to make the effort of moving from a batch to a real-time recommendation setting.INDEX TERMS A/B tests, collaborative filtering, job recommendations, real-time recommendations, RP3Beta.

show abstract

“…To improve the performance of online adaptive learning algorithms in stream-based recommender systems for web activities, it is important to consider the temporal evolution of modeled concepts due to a change in the distribution of log data or a change in the relation between data and target variable (i.e. concept drift) [7,40,96]. Considering a butterfly as two users with mutual preferences and two items with mutual perceptions, our work impacts modeling the parallel drift of concepts such as user preferences and item perception.…”

Section: Introductionmentioning

confidence: 99%

Scale-Invariant Strength Assortativity of Streaming Butterflies

Sheshbolouki¹,

Özsu²

2021

Preprint

View full text Add to dashboard Cite

Bipartite graphs are rich data structures with prevalent applications and identifier structural features. However, less is known about their growth patterns, particularly in streaming settings. Current works study the patterns of static or aggregated temporal graphs optimized for certain down-stream analytics or ignoring multipartite /non-stationary data distributions, emergence patterns of subgraphs, and streaming paradigms. To address these, we perform statistical network analysis over web log streams and identify the governing patterns underlying the bursty emergence of mesoscopic building blocks, 2,2-bicliques known as butterflies, leading to a phenomenon that we call "scale-invariant strength assortativity of streaming butterflie". We provide the graph-theoretic explanation of this phenomenon. We further introduce a set of micro-mechanics in the body of a streaming growth algorithm, sGrow, to pinpoint the generative origins. sGrow supports streaming paradigms, emergence of 4-vertex graphlets, and provides user-specified configurations for the scale, burstiness, level of strength assortativity, probability of out-of-order records, generation time, and time-sensitive connections. Comprehensive Evaluations on pattern reproducing and stress testing validate the effectiveness, efficiency, and robustness of sGrow in realization of the observed patterns independent of initial conditions, scale, temporal characteristics, and model configurations. Theoretical and experimental analysis verify the robust ability of sGrow in generating streaming graphs based on user-specified configurations that affect the scale and burstiness of the stream, level of strength assortativity, probability of-of-order streaming records, generation time, and time-sensitive connections.

show abstract

A Survey on Stream-Based Recommender Systems

Cited by 23 publications

References 104 publications

A Survey on Incremental Update for Neural Recommender Systems

A Survey on Incremental Update for Neural Recommender Systems

Comparison of Real-Time and Batch Job Recommendations

Scale-Invariant Strength Assortativity of Streaming Butterflies

Contact Info

Product

Resources

About