Improving End-to-End Sequential Recommendations with Intent-aware Diversification

Chen, Wanyu; Ren, Pengjie; Cai, Fei; Sun, Fei; Rijke, Maarten de

doi:10.1145/3340531.3411897

Cited by 53 publications

(28 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to persistent groups often have stable members and rich historical interactions [43,65], previous studies [13,31,50] on this kind of group were mainly focused on treating groups as pseudousers, and then adopt conventional personalized recommendation techniques [12,14] for making group recommendations. For example, to estimate the rating that a group of members might give to an item, Chen et al [13] proposed a genetic algorithm-based recommendation method by predicting the possible interactions among group members.…”

Section: Persistent Group Recommendationmentioning

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

Section: Persistent Group Recommendationmentioning

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

show abstract

“…Filter bubbles and related biases have been studied in the context of recommender systems [26], with recent work studying e-commerce websites [10] and widely-used algorithms [48]. One approach that has been explored for mitigating these biases is judging recommendations not only by accuracy, but with other metrics such as diversity (difference between recommendations) [6,46], novelty (items assumed unknown to the user) [47], and serendipity (a measure of relevance and surprise associated with a positive emotional response) [44].…”

Section: Related Workmentioning

confidence: 99%

“…They may lead scientists to concentrate on narrower niches [18], reinforcing citation inequality and bias [27] and limiting cross-fertilization among different areas that could catalyze innovation [13]. Addressing filter bubbles in general, in domains such as social media and e-commerce recommendations, is a hard and unsolved problem [6,10,48]. The problem is especially difficult in the scientific domain.…”

Section: Introductionmentioning

confidence: 99%

Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery

Portenoy¹,

Radensky²,

West³

et al. 2021

Preprint

View full text Add to dashboard Cite

Scientific silos can hinder innovation. These information "filter bubbles" and the growing challenge of information overload limit awareness across the literature, making it difficult to keep track of even narrow areas of interest, let alone discover new ones. Algorithmic curation and recommendation, which often prioritize relevance, can further reinforce these bubbles. In response, we describe Bridger, a system for facilitating discovery of scholars and their work, to explore design tradeoffs among relevant and novel recommendations. We construct a faceted representation of authors using information extracted from their papers and inferred personas. We explore approaches both for recommending new content and for displaying it in a manner that helps researchers to understand the work of authors who they are unfamiliar with. In studies with computer science researchers, our approach substantially improves users' abilities to do so. We develop an approach that locates commonalities and contrasts between scientists-retrieving partially similar authors, rather than aiming for strict similarity. We find this approach helps users discover authors useful for generating novel research ideas of relevance to their work, at a higher rate than a state-of-art neural model. Our analysis reveals that Bridger connects authors who have different citation profiles, publish in different venues, and are more distant in social co-authorship networks, raising the prospect of bridging diverse communities and facilitating discovery.

show abstract

“…After that, we combine 𝑐 2 and 𝑢 1 to get the recombined preferences 𝑃 ′ 1 , and we combine 𝑐 1 and 𝑢 2 to get the recombined preferences 𝑃 ′ 2 through the preference recombination operation. Based on the above process, we can devise two types of SSL signals: (1) We use the recombined preferences to predict the next item in both sequences; and (2) We require that the recombined preferences (e.g., 𝑃 ′ 1 ) are as similar as possible to the original preferences (e.g., 𝑃 1 ), and that the common preference representations are close to each other (i.e., 𝑐 1 = 𝑐 2 ). By doing so, we force the preference extraction model to learn how to identify and edit user preferences so as to do better user preference extraction and representation.…”

Section: Introductionmentioning

confidence: 99%

“…For example, in Figure 1, the traditional methods only obtain a mixed preference representation for each sequence while they ignore relations between other sequences. Recent research has investigated how to identify multiple preferences through a multi-head attention mechanism on top of RNN-based methods [1,2,8]. But to the best of our knowledge, this has not been explored in transformer-based methods.…”

Section: Introductionmentioning

confidence: 99%

Improving Transformer-based Sequential Recommenders through Preference Editing

Ma¹,

Ren²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

One of the key challenges in sequential recommendation (SR) is how to extract and represent user preferences. Traditional SR methods rely on the next item as the supervision signal to guide preference extraction and representation. We propose a novel learning strategy, named preference editing. The idea is to force the SR model to discriminate the common and unique preferences in different sequences of interactions between users and the recommender system. By doing so, the SR model is able to learn how to identify common and unique user preferences, and thereby do better user preference extraction and representation. We propose a transformer based SR model, named MrTransformer (Multi-preference Transformer), that concatenates some special tokens in front of the sequence to represent multiple user preferences and makes sure they capture different aspects through a preference coverage mechanism. Then, we devise a preference editing-based self-supervised learning mechanism for training MrTransformer that contains two main operations: preference separation and preference recombination. The former separates the common and unique user preferences for a given pair of sequences. The latter swaps the common preferences to obtain recombined user preferences for each sequence. Based on the preference separation and preference recombination operations, we define two types of self-supervised learning loss that require that the recombined preferences are similar to the original ones, and that the common preferences are close to each other.We carry out extensive experiments on two benchmark datasets. MrTransformer with preference editing significantly outperforms state-of-the-art SR methods in terms of Recall, MRR and NDCG. We find that long sequences whose user preferences are harder to extract and represent benefit most from preference editing.

show abstract

Improving End-to-End Sequential Recommendations with Intent-aware Diversification

Cited by 53 publications

References 43 publications

Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation

Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation

Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery

Improving Transformer-based Sequential Recommenders through Preference Editing

Contact Info

Product

Resources

About