Social-Enhanced Attentive Group Recommendation

Cao, Da; He, Xiangnan; Miao, Lianhai; Xiao, Guangyi; Chen, Hao; Xu, Jing

doi:10.1109/tkde.2019.2936475

Cited by 87 publications

(42 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Candidatebased retrieval methods attempt to bridge the semantic gap between language and video by obtaining pre-segmented video moments and further perform the cross-modal retrieval. Benefiting from the merit of neural attention network [2][3][4], the methods of attentive cross-modal retrieval network [22], cross-modal temporal moment localization [23], and spatial and language-temporal attention model [17] are introduced. By jointly learning the embedding space of visual and textual content, the dependency between vision and language are well learnt to boost the language-video moment retrieval performance [39,41,42].…”

Section: Video Moment Retrievalmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Video Moment Retrieval by Jointly Modeling Ranking and Localization

Cao

Zeng

Wei

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Retrieving video moments from an untrimmed video given a natural language as the query is a challenging task in both academia and industry. Although much effort has been made to address this issue, traditional video moment ranking methods are unable to generate reasonable video moment candidates and video moment localization approaches are not applicable to large-scale retrieval scenario. How to combine ranking and localization into a unified framework to overcome their drawbacks and reinforce each other is rarely considered. Toward this end, we contribute a novel solution to thoroughly investigate the video moment retrieval issue under the adversarial learning paradigm. The key of our solution is to formulate the video moment retrieval task as an adversarial learning problem with two tightly connected components. Specifically, a reinforcement learning is employed as a generator to produce a set of possible video moments. Meanwhile, a pairwise ranking model is utilized as a discriminator to rank the generated video moments and the ground truth. Finally, the generator and the discriminator are mutually reinforced in the adversarial learning framework, which is able to jointly optimize the performance of both video moment ranking and video moment localization. Extensive experiments on two well-known datasets have well verified the effectiveness and rationality of our proposed solution. CCS CONCEPTS • Information systems → Multimedia and multimodal retrieval; • Theory of computation → Adversarial learning; Reinforcement learning.

show abstract

Section: Video Moment Retrievalmentioning

confidence: 99%

“…As for each iteration, the generator's parameters are updated with the help of Eqn. (3). The discriminator D ϕ optimizes the BPR ranking loss and the semantic consistency loss,…”

Section: Adversarial Learningmentioning

confidence: 99%

Adversarial Video Moment Retrieval by Jointly Modeling Ranking and Localization

Cao

Zeng

Wei

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…to form social groups and participate in activities in groups [19,67], such as group tours, class reunion, and family dinners. It is becoming essential to develop group recommender systems [9,33,61,62] to provide groups with appropriate recommendations (e.g., recommend a restaurant or a concert).…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation

Guo

Yin

Chen

et al. 2021

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Group recommendation aims to recommend items to a group of users. In this work, we study group recommendation in a particular scenario, namely occasional group recommendation, where groups are formed ad hoc and users may just constitute a group for the first time—that is, the historical group-item interaction records are highly limited. Most state-of-the-art works have addressed the challenge by aggregating group members’ personal preferences to learn the group representation. However, the representation learning for a group is most complex beyond the aggregation or fusion of group member representation, as the personal preferences and group preferences may be in different spaces and even orthogonal. In addition, the learned user representation is not accurate due to the sparsity of users’ interaction data. Moreover, the group similarity in terms of common group members has been overlooked, which, however, has the great potential to improve the group representation learning. In this work, we focus on addressing the aforementioned challenges in the group representation learning task, and devise a hierarchical hyperedge embedding-based group recommender, namely HyperGroup. Specifically, we propose to leverage the user-user interactions to alleviate the sparsity issue of user-item interactions, and design a graph neural network-based representation learning network to enhance the learning of individuals’ preferences from their friends’ preferences, which provides a solid foundation for learning groups’ preferences. To exploit the group similarity (i.e., overlapping relationships among groups) to learn a more accurate group representation from highly limited group-item interactions, we connect all groups as a network of overlapping sets (a.k.a. hypergraph), and treat the task of group preference learning as embedding hyperedges (i.e., user sets/groups) in a hypergraph, where an inductive hyperedge embedding method is proposed. To further enhance the group-level preference modeling, we develop a joint training strategy to learn both user-item and group-item interactions in the same process. We conduct extensive experiments on two real-world datasets, and the experimental results demonstrate the superiority of our proposed HyperGroup in comparison to the state-of-the-art baselines.

show abstract

“…It also gives people the ability to plan and organize group activities, which is an essential part of daily life. This needs an in-depth study of the group recommender system (GRS), which suggests items to a group of users considering their collective preferences (Cao et al, 2019;Dara, Chowdary, & Kumar, 2020;Quijano-Sánchez, Recio-García, & Díaz-Agudo, 2010). In addition, the data generated by these networks makes it possible to reveal the behavior patterns of users and add them to recommender systems (Christoforidis, Kefalas, Papadopoulos, & Manolopoulos, 2019).…”

Section: Introductionmentioning

confidence: 99%

Behavior‐based POI recommendation for small groups in location‐based social networks

Sojahrood

Taleai

2021

Transactions in GIS

View full text Add to dashboard Cite

In point-of-interest (POI) group recommender systems, suggesting the most suitable visit places for a heterogeneous group in which members are far from each other would be difficult in terms of finding a consensus among group members. In this article, we argue that the geographical proximity of POIs to users' locations has a notable influence on group decisions to visit the POI and their check-in behavior. We develop a new geographical model based on the check-in behavior of the group in location-based social networks to improve group recommendations by introducing a new concept called users' spatial ratio in a group vectors and using a 2D kernel density estimation method. To evaluate the performance of

show abstract

Social-Enhanced Attentive Group Recommendation

Cited by 87 publications

References 37 publications

Adversarial Video Moment Retrieval by Jointly Modeling Ranking and Localization

Adversarial Video Moment Retrieval by Jointly Modeling Ranking and Localization

Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation

Behavior‐based POI recommendation for small groups in location‐based social networks

Contact Info

Product

Resources

About