An enhanced probabilistic fairness-aware group recommendation by incorporating social activeness
Introduction
Traditional recommender systems (RSs) aim to provide appropriate services for a single user based on her preferences. Such RSs have been deployed in a wide range of areas such as music (Yahoo), restaurants (Foursquare), and hiking (Meetup). However, many contexts requires recommending to a group of users (i.e., group recommendation) while various preferences of all the group members should be considered. For example, in cases of selecting a picnic location for a group of friends, recommending a restaurant for a company's annual meeting, arranging attractions for a group of tourists, the traditional individual recommendation methods no longer fit.
Group recommendation is more complicated than individual recommendation. Since group members may have different preferences (Yuan et al., 2014; Carvalho and Macedo, 2013a), a service preferred by one user may not satisfy another user's taste. Moreover, each user hopes her preferred service to appear at a top position in the service list recommended to her group. According to the studies in the fair division of sources (Manurangsi and Suksompong, 2017; Aleksandrov et al., 2015; Herreiner and Puppe, 2009), a recommended services list is fair to a user if and only if her preferred service is ranked at a top position (Serbos et al., 2017). Therefore, it is of paramount importance to recommend a ranked service list that is fair to every user, i.e., fairness. An ideal recommendation approach for group not only guarantee the accuracy but also efficiently solve fairness issue.
Most current studies on group recommendation (Baltrunas et al., 2010; Liu et al., 2012; Rakesh et al., 2016; Yuan et al., 2014; Quijano-Sanchez et al., 2013; Salehi-Abari and Boutilier, 2014; Ronen et al., 2014) determines the services that satisfy the group members' preferences via modelling users' implicit peer influence (Yuan et al., 2014). However, they cannot solve the fairness issue because they commonly lack a proper method to balance the various preferences. Other studies (Serbos et al., 2017; Xiao et al., 2017; Zhang et al., 2017; Carvalho and Macedo, 2013a, 2013b) convert the fairness issue into a comparison sequencing problem and design a preference-based sequencing strategy to rank the recommended services. Although this strategy can ensure fairness to some extent, it cannot tackle the scenarios where group members have conflicting preferences. As it is intractable to compare users' preference (e.g., distinguish the optimal options from spicy and light food preferences), the recommended list derived by this strategy can only guarantees a part of users' preferences instead of all the users’ preferences. Therefore, sequencing strategy based on preference is improper.
Fortunately, the social regularization principle (O'Hara, 1999) provides a interesting viewpoint: the more contribution you pay, the more priority or return you win (Marx, 2008). For a group, its formation and sustainability heavily depends on its members' activeness, which refers to as the frequency of users' interactions including sharing information or extending the social circle (Turner, 1982). Inspired by the social regularization principle, it is more intuitive and proper to consider users' activeness when ranking services, i.e., a user's preference should be satisfied in priority if she contributes to the group more actively. Different from dealing with users' preferences, we can easily quantify users' activeness via simple statistic methods (Koller et al., 2007) and handle conflicting user preferences. For example, we can count up how many friends a user has or how much shopping information she shares.
We borrow the fairness definition from (Serbos et al., 2017; Xiao et al., 2017) and propose a novel two-stage group recommendation model called PFGR. PFGR couples user's various preferences and activeness, which has seldom been studied by previous work. PFGR consists of two parts: multi-facet probabilistic graph model (MFPG) and activeness-based coalition game strategy (ACG). During recommendation, PFGR first applies MFPG to produce the services which satisfy all the members' preferences by modeling several observations (see Section 3.5) obtained from the real life. Then, it utilizes ACG to rank these services to attain a trade-off among various preferences.
Specifically, MFPG is a probabilistic generative model that aims to select the services preferred by a group. It is developed on latent Dirichlet allocation (LDA), which has been proven successful in modeling implicit interactions (Blei et al., 2003; Jelodar et al., 2017). Compared with other group recommendation model based on LDA (Yuan et al., 2014; Rakesh et al., 2016), MFGP considers more implicit interactions such as users' social links, preferences influence, and common-interest. In particular, considering users' implicit interactions can help group members to better select their desired services. ACG is inspired by the coalition game theory, which has two advantages when compared with current sequencing strategy based on the greedy algorithm (Serbos et al., 2017; Xiao et al., 2017) or the non-cooperative game theory (Zhang et al., 2017; Carvalho and Macedo, 2013b): 1) instead of considering a single user's preference, the coaliton game theory innately considers users' peer influence (e.g., common-interest, social links) and therefore conforms to the fact that a user's selection may be affected by others; 2) the coalition game theory considers the balance between several coalitions. That makes it easier to find the equilibrium among a large number of users in a dynamic environment where each user's preferences may change over time.
We make the following contributions in this paper:
- ∙
We propose a novel two-stage group recommendation approach named PFGR which both guarantee the accuracy of recommendation and efficiently solve fairness issue. PFGR couples users' preferences and activeness, which has not been well studied before.
- ∙
we design an activeness-based sequencing strategy to ranking services following the social regularization principle to promote the fairness in recommendation. This strategy can better solve conflicted preference contexts when compared with the traditional preference-based sequencing strategy.
- ∙
We conduct extensive experiments to validate the effectiveness of PFGR under various settings on three real data sets. The evaluation results show our scheme consistently outperforms state-of-the-art approaches when considering the fairness simultaneously.
The rest of this paper is organized as follows: Section 2 reviews the related work. Section 3 introduces the preliminaries and formulates the group recommendation problem. Section 4 presents the details of our proposal, including the MFPG model and ACG strategy. Section 5 reports our analysis of experiment results. Finally, Section 6 concludes the paper.
Section snippets
Group recommendation
Generally, group recommendation methods can be divided into two categories: the preference aggregation method and the score aggregation method (Amer-Yahia et al., 2009). The former method first aggregates the profiles of the group members into one file, i.e., constructs a virtual user, and then make recommendations to this virtual user (Seko et al., 2011; Hu et al., 2014). The latter, on the contrary, first produces recommendations for each group member, then aggregates their recommendation
Preliminaries
In this section, we first introduce some preliminaries and problem formulation, then provide several observations concluded from the real world. The main notations used in this paper are listed in Table 1.
Scheme design
Our proposed scheme is two-stage model: multi-facet probabilistic graph model (MFPG) and activeness-based coalition ranking strategy (ACG). MFPG aims to assist a group to select the services preferred by all the group users based on preferences. After that, ACG will rank the position of these services to guarantee fairness according to users’ activeness. We describe them separately.
Data sets and statistics
To validate the performance, we apply our scheme to three real-world data sets. Table 2 shows the statistics of data sets (items in this section are identical to the services mentioned above).
- ∙
Epinions1: Tang (Tang et al., 2012) crawled it from a well-known online consumer review site Epinions. On this site, a user writes not only critical reviews for various products but also adds other members to his trusted list if he feels that their reviews are
Conclusions
In this paper, we mainly study the fairness problem in group recommendation based on probabilistic graph model and coalition game and propose a novel approach called PFGR which can achieve higer recommendation performance with fairness account. The proposed approach first selects the services satisfied the preferences of a group via modelling the selection behavior of users according to several observations existing in the real world. After determining the services, PFGR further considers
CRediT authorship contribution statement
Yang Xiao: Conceptualization, Methodology, Software, Investigation, Data curation, Writing - original draft, Writing - review & editing. Qingqi Pei: Supervision, Funding acquisition. Lina Yao: Writing - review & editing, Supervision, Project administration. Shui Yu: Resources. Lei Bai: Writing - review & editing. Xianzhi Wang: Resources.
Acknowledgements
This work is supported by the National Key Research and Development Program of China under Grant 2018YFE0126000, the Key Program of NSFC-Tongyong Union Foundation under Grant U1636209, the National Natural Science Foundation of China under Grant 61902292, and the Key Research and Development Programs of Shaanxi under Grant 2019ZDLGY13-07 and 2019ZDLGY13-04.
References (50)
- et al.
Factored similarity models with social trust for top-n item recommendation
Knowl. Base Syst.
(2017) - et al.
Asymptotic existence of fair divisions for groups
Math. Soc. Sci.
(2017) - et al.
A trust-based probabilistic recommendation model for social networks
J. Netw. Comput. Appl.
(2015) - et al.
A game theory-based trust measurement model for social networks
Comput. Soc. Netw.
(2016) - et al.
A survey of collaborative filtering based social recommender systems
Comput. Commun.
(2014) - et al.
Online fair division: analysing a food bank problem
- et al.
Group recommendation: Semantics and efficiency
Proceed. VLDB Endow.
(2009) - et al.
Social Relationships
(2013) - et al.
Group recommendations with rank aggregation and collaborative filtering
- et al.
Characterizing user behavior in online social networks
Latent dirichlet allocation
J. Mach. Learn. Res.
Crowd-voting-based group recommender systems
Abordagens de teoria dos jogos para modelagem de sistemas de recomendao para grupos
Generation of coalition structures to provide proper groups' formation in group recommender systems
Users' satisfaction in recommendation systems for groups: an approach based on noncooperative games
A gts allocation scheme to improve multiple-access performance in vehicular sensor networks
IEEE Trans. Veh. Technol.
An intelligent robust networking mechanism for the internet of things
IEEE Commun. Mag.
A multi-view deep learning approach for cross domain user modeling in recommendation systems
Applied Game Theory and Strategic Behavior
Envy freeness in experimental fair division problems
Theor. Decis.
Deep modeling of group preferences for group-based recommendation
AAAI
Latent Dirichlet Allocation (Lda) and Topic Modeling: Models, Applications, a Survey, Multimedia Tools and Applications
Cvcg: cooperative v2v-aided transmission scheme based on coalitional game for popular content distribution in vehicular ad-hoc networks
IEEE Trans. Mobile Comput.
Introduction to Statistical Relational Learning
Voting based group recommendation: how users vote
Cited by (17)
Categorization of knowledge graph based recommendation methods and benchmark datasets from the perspectives of application scenarios: A comprehensive survey
2022, Expert Systems with ApplicationsCitation Excerpt :Bonner & Vasile, 2018) Learned the proposed model on logged data that contained the recommendation results from biased strategy and predicted their own distracted recommendation results based on random users’ exposures. PFGR (Xiao et al., 2020) combined the probabilistic technique with coalition game theory to guarantee the presence of fairness between the merchandising parties and the users. They treated the connections present between the groups of users and the sets of services as the relations among vertices in the graph; and imposed fairness ensuring constraints on the decision.
Towards comprehensive profile aggregation methods for group recommendation based on the latent factor model
2021, Expert Systems with ApplicationsCitation Excerpt :For the group members’ weights used in the rating average, emphasis should be placed on the fact that the ratings of influential members should be more important than those of the others. Therefore, to identify their values, some authors have relied on external data sources, such as social information (Gartrell et al., 2010; Quijano-Sanchez, Recio-Garcia, Diaz-Agudo, & Jimenez-Diaz, 2013; Ye, Liu, & Lee, 2012; Yin et al., 2019); trust links between members (Wu, Zhang, Liu, & Cao, 2019; Wang, Chen, et al., 2020; Xiao et al., 2020); tags (Amer-Yahia, Roy, Chawlat, Das, & Yu, 2009; Liu, Hua, Yang, Wang, & Zhang, 2009; Roy, Amer-Yahia, Chawla, Das, & Yu, 2010); domain knowledge (Ardissono et al., 2003, 2005; Berkovsky & Freyne, 2010a; Vildjiounaite, Kyllönen, Hannula, & Alahuhta, 2009); members’ roles in a family (Berkovsky & Freyne, 2010a); Interactions between members (Garcia & Sebastia, 2014; Guo et al., 2020; Jeong & Kim, 2019; McCarthy et al., 2006; Villavicencio et al., 2019); members’ locations (Sojahrood & Taleai, 2021). However, it is not always possible for recommender systems to interact with these data sources.
MutualRec: Joint friend and item recommendations with mutualistic attentional graph neural networks
2021, Journal of Network and Computer ApplicationsCitation Excerpt :Social link prediction. Link prediction aims to predict the potential new links for a target user based on the partially observed links in a social network (Xiao et al., 2020a, 2020b). Early work (He et al., 2015) uses non-negative matrix factorization to predict the unknown value of friendship.
Fairness in recommender systems: research landscape and future directions
2024, User Modeling and User-Adapted Interaction