Latent factor models and aggregation operators for collaborative filtering in reciprocal recommender systems

Neve, James; Palomares, Iván

doi:10.1145/3298689.3347026

Cited by 33 publications

(26 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We hypothesised that ImRec would perform better than collaborative filtering algorithms in cold-start situations. We tested ImRec against the current best in class collaborative filtering algorithm, LFRR [22]. Using all available data, LFRR outperforms ImRec.…”

Section: Cold-start Resultsmentioning

confidence: 99%

“…Kleinerman et al designed a modification to RCF to account for user popularity [2] and also tested explanations for the recommendations made by RCF, finding that users provided with explanations for their recommendations were more likely to use them [3]. Neve et al designed a collaborative filtering algorithm based on latent factors, and found that this improved on the efficiency of RCF on large datasets [22]. There has also been research performed on alternative aggregation operators to the harmonic mean for combining unidirectional preference scores into a bidirectional relation, finding that depending on the situation, different operators were likely to be more or less appropriate [21].…”

Section: Reciprocal Recommendationmentioning

confidence: 99%

“…Content-based filtering algorithms therefore often form part of hybrid systems that improve on the results of the collaborative filtering algorithm, often by operating in cold start situations where they can outperform collaborative filtering techniques [4]. It would be interesting to test ImRec as part of a hybrid RRS that improves on the results of existing algorithms such as LFRR [22], for example in a switching hybrid system [6] that moves from content-based to collaborative reciprocal recommendation when sufficient data is available.…”

Section: Future Workmentioning

confidence: 99%

“…There are a number of examples of collaborative filtering-based RRSs in the literature [26] [22]. However, besides RECON [20], a categorical content-based RRS, there are very few examples of content-based reciprocal recommendation.…”

mentioning

confidence: 99%

See 3 more Smart Citations

ImRec: Learning Reciprocal Preferences Using Images

Neve

McConville

2020

Fourteenth ACM Conference on Recommender Systems

Self Cite

View full text Add to dashboard Cite

Reciprocal Recommender Systems are recommender systems for social platforms that connect people to people. They are commonly used in online dating, social networks and recruitment services. The main difference between these and conventional user-item recommenders that might be found on, for example, a shopping service, is that they must consider the interests of both parties. In this study, we present a novel method of making reciprocal recommendations based on image data. Given a user's history of positive and negative preference expressions on other users images, we train a siamese network to identify images that fit a user's personal preferences. We provide an algorithm to interpret those individual preference indicators into a single reciprocal preference relation. Our evaluation was performed on a large real-world dataset provided by a popular online dating service. Based on this, our service significantly improves on previous state-of-the-art content-based solutions, and also out-performs collaborative filtering solutions in cold-start situations. The success of this model provides empirical evidence for the high importance of images in online dating.

show abstract

Section: Cold-start Resultsmentioning

confidence: 99%

Section: Reciprocal Recommendationmentioning

confidence: 99%

Section: Future Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

ImRec: Learning Reciprocal Preferences Using Images

Neve

McConville

2020

Fourteenth ACM Conference on Recommender Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nowadays, the most popular online dating Web applications could even have several hundreds of millions of registered users. Consequently, an effective reciprocal recommendation system (Neve and Palomares 2019;Ting, Lo, and Lin 2016;Palomares 2020) is urgently needed to enhance user experience. Generally, the reciprocal recommendation problem aims to recommend a list of users to another user that best matches their mutual interests (Pizzato et al 2013;Zheng et al 2018).…”

Section: Introductionmentioning

confidence: 99%

A Motif-Based Graph Neural Network to Reciprocal Recommendation for Online Dating

Luo

Li²,

Peng

et al. 2020

Neural Information Processing

View full text Add to dashboard Cite

Recently, the reciprocal recommendation, especially for online dating applications, has attracted more and more research attention. Different from conventional recommendation problems, the reciprocal recommendation aims to simultaneously best match users' mutual preferences. Intuitively, the mutual preferences might be affected by a few key attributes that users like or dislike. Meanwhile, the interactions between users' attributes and their key attributes are also important for key attributes selection. Motivated by these observations, in this paper we propose a novel reinforced random convolutional network (RRCN) approach for the reciprocal recommendation task. In particular, we technically propose a novel random CNN component which can randomly convolute nonadjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation. Moreover, we design a reinforcement learning based strategy to integrate with the random CNN component to select salient attributes to form the candidate set of key attributes. We evaluate the proposed RRCN against a number of both baselines and the state-of-the-art approaches on two real-world datasets, and the promising results have demonstrated the superiority of RRCN against the compared approaches in terms of a number of evaluation criteria.

show abstract

People-to-People Reciprocal Recommenders

Koprinska¹,

Yacef²

2012

Recommender Systems Handbook

View full text Add to dashboard Cite

Latent factor models and aggregation operators for collaborative filtering in reciprocal recommender systems

Cited by 33 publications

References 26 publications

ImRec: Learning Reciprocal Preferences Using Images

ImRec: Learning Reciprocal Preferences Using Images

A Motif-Based Graph Neural Network to Reciprocal Recommendation for Online Dating

People-to-People Reciprocal Recommenders

Contact Info

Product

Resources

About