Diversifying Group Recommendation

Toan, Nguyen Thanh; Cong, Phan Thanh; Tâm, Nguyễn Thành; Hùng, Nguyễn Quốc; Stantić, Bela

doi:10.1109/access.2018.2815740

Cited by 14 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a node adjacency matrix or Laplacian matrix), and factorisation techniques are then directly applied to this matrix to obtain the embeddings [33], [37]- [39]. Random walk methods generate random walks starting from the network nodes, and then learn the embeddings for the nodes so that these embeddings can capture the co-occurrences of nodes in the walks [22], [23], [40]. Deep learning methods leverage neural architectures [41], [42] such as graph neural networks [43] and autoencoders to incorporate the node features and an inductive capability in the same model [44]- [46].…”

Section: A Graph Embeddingmentioning

confidence: 99%

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

Huynh

Tong

Nguyên

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Location-based social networks (LBSNs) have emerged over the past few years. Their exponential network effects depend on the fact that each user can share her daily digital footprints with different communities, in different places, and at different times (for example in the form of check-in activities). Unlike other types of social networks, activities in an LBSN can potentially be performed by several users in a collaborative way. Existing studies of representation learning for LBSNs often consider them as regular graphs and ignore these high-order, dynamic, and multi-role contexts, since their holistic interactions are quite difficult to capture. In this paper, we propose a model in which these holistic interactions can be learned and transferred into node embeddings derived from a hypergraph representation and a persona decomposition process. More specifically, the model learns from friendship edges, check-in hyperedges, and node personas at the same time, and devises multiple presentations for each user that reflects their multiple roles in a social context. The embedding learning process also exploits useful patterns such as user colocation and sequential effects through a carefully designed point-of-interest splitting step. Extensive experiments on real and synthetic datasets show that our model outperforms alternative state-of-the-art embedding methods on friendship and location prediction tasks by an average margin of 45.7% and 29.46%, respectively. We also demonstrate the robustness of our model against adversarial conditions such as structural noise, attribute noise, and hyperparameter sensitivity.

show abstract

Section: A Graph Embeddingmentioning

confidence: 99%

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

Huynh

Tong

Nguyên

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…Group recommendation has received much study in the literature from a variety of angles, including aggregation techniques [1], [5], group consensus [3] and graph-based algorithms [8]. However, the use of diversity algorithms in GRS is yet a low explored field [6].…”

Section: Related Workmentioning

confidence: 99%

“…Their appearance frequency score is calculated over the user's rating predictions. [6] also discuss the problem of diversity in GRS. However, their experiments ran over synthetic groups rather than real ones.…”

Section: Related Workmentioning

confidence: 99%

“…Group size: The size of the group can vary drastically even in real life, from a couple having lunch to a crowd of thousands in a football stadium. In our experiments, we set the group size to 3 or 5, also inspired by recurrent use in the literature [17] and [6]. Cohesion between members: This aspect focuses on the relationship between members.…”

Section: B the Group Modelmentioning

confidence: 99%

“…Diversity in RS has been extensively researched in the literature in recent years. The first work to formally introduce the concept of diversity was [4], [5] explore diversity while evaluating RS, and [6] discuss the effects of diversity algorithms in group recommendations. By addressing the issue of overspecialization in diversity for group recommendation, this article seeks to contribute to this particular field of research.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating Diversification in Group Recommender Systems

Oliveira¹,

Durão²

2022

Communication Papers of the 17th Conference on Computer Science and Intelligence Systems

View full text Add to dashboard Cite

The formation of groups is an ordinary event in our routines. For example, people used to lunch, travel, or hang out in groups. Conversely, getting a consensus over an item may be difficult for some groups as the number of digital information increases. Group Recommender Systems (GRS) rise to assist in this task, as they filter which items may be more relevant to the group. Although there are consensus techniques to help in this matter, recommendations to groups can become monotonous, and this opens space for applying diversification techniques to improve recommendations. In this paper, we expose a model for recommendation to groups using diversification techniques and present the results of the online experiment where the proposal obtained an increase in precision at all levels compared with baseline.

show abstract