Group-Aware Long- and Short-Term Graph Representation Learning for Sequential Group Recommendation

Group recommendation is a special service type which has the ability to satisfy a group’s common interest and find the preferred items for group users. Deep mining of trust relationship between group members can contribute to the improvement of accuracy during group recommendation. Most of the existing trust-based group recommendation methods pay little attention to the diversity of trust sources, resulting in poor recommendation accuracy. To address the problem above, this paper proposes a group recommendation method based on a hybrid trust metric (GR-HTM). Firstly, GR-HTM creates an attribute trust matrix and a social trust matrix based on user attributes and social relationships, respectively. Secondly, GR-HTM accomplishes a hybrid trust matrix based on the integration of these two matrices with the employment of the Tanimoto coefficient. Finally, GR-HTM calculates weights for each item in the hybrid trust matrix based on weighted-meanlist and proceeds to group recommendation with a given trust threshold. Simulation experiments demonstrate that the proposed GR-HTM has better performance for group recommendation in accuracy and effectiveness.

Group Recommendation (GR) is the task of suggesting relevant items/events for a group of users in online systems, whose major challenge is to aggregate the preferences of group members to infer the decision of a group. Prior group recommendation methods applied predefined static strategies for preference aggregation. However, these static strategies are insufficient to model the complicated decision making process of a group, especially for occasional groups which are formed adhoc. Compared to conventional individual recommendation task, GR is rather dynamic and each group member may contribute differently to the final group decision. Recent works argue that group members should have non-uniform weights in forming the decision of a group, and try to utilize a standard attention mechanism to aggregate the preferences of group members, but they do not model the interaction behavior among group members, and the decision making process is largely unexplored.In this work, we study GR in a more general scenario, that is Occasional Group Recommendation (OGR), and focus on solving the preference aggregation problem and the data sparsity issue of group-item interactions. Instead of exploring new heuristic or vanilla attention-based mechanism, we propose a new social self-attention based aggregation strategy by directly modeling the interactions among group members, namely Group Self-Attention (GroupSA). In GroupSA, we treat the group decision making process as multiple voting processes, and develop a stacked social self-attention network to simulate how a group consensus is reached. To overcome the data sparsity issue, we resort to the relatively abundant user-item and user-user interaction data, and enhance the representation of users by two types of aggregation methods. In the training process, we further propose a joint training method to learn the user/item embeddings in the group-item recommendation task and the user-item recommendation task simultaneously. Finally, we conduct extensive experiments on two real-world datasets. The experimental results demonstrate the superiority of our proposed GroupSA method compared to several state-of-the-art methods in terms of HR and NDCG.

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.

The emerging topic of sequential recommender (SR) has attracted increasing attention in recent years, which focuses on understanding and learning the sequential dependencies of user behaviors hidden in the user-item interactions. Previous methods focus on capturing the point-wise sequential dependencies with considering the time evenly spaced. However, in the real world, the time and semantic irregularities are hidden in the user’s successive actions. Meanwhile, with the tremendous increase of users and items, the hardness of modeling user interests from spare explicit feedback. To this end, we seek to explore the influence of item-aspect reviews sequence with varied time intervals on sequential modeling. We present RTiSR, a review-driven time interval-aware sequential recommendation framework, to predict the user’s next purchase item by jointly modeling the sequence dependencies from aspect-aware reviews. The main idea is twofold: (1) explicitly learning user and item representation from reviews by assigning different weights, and (2) leveraging a hybrid neural network to capture the collective sequence patterns with a flexible order from aspect-aware review sequences. We conduct extensive experiments on industrial datasets to evaluate the effectiveness of RTiSR. Experimental results demonstrate the superior performance of RTiSR in different evaluation metrics, compared to the state-of-the-art competitors.

Self-attention models have achieved the state-of-the-art performance in sequential recommender systems by capturing the sequential dependencies among user–item interactions. However, they rely on adding positional embeddings to the item sequence to retain the sequential information, which may break the semantics of item embeddings due to the heterogeneity between these two types of embeddings. In addition, most existing works assume that such dependencies exist solely in the item embeddings, but neglect their existence among the item features. In our previous study, we proposed a novel sequential recommendation model, i.e., MLP4Rec, based on the recent advances of MLP-Mixer architectures, which is naturally sensitive to the order of items in a sequence because matrix elements related to different positions of a sequence will be given different weights in training. We developed a tri-directional fusion scheme to coherently capture sequential, cross-channel, and cross-feature correlations with linear computational complexity as well as much fewer model parameters than existing self-attention methods. However, the cascading mixer structure, the large number of normalization layers between different mixer layers, and the noise generated by these operations limit the efficiency of information extraction and the effectiveness of MLP4Rec. In this extended version, we propose a novel framework – SMLP4Rec for sequential recommendation to address the aforementioned issues. The new framework changes the flawed cascading structure to a parallel mode, and integrates normalization layers to minimize their impact on the model’s efficiency while maximizing their effectiveness. As a result, the training speed and prediction accuracy of SMLP4Rec are vastly improved in comparison to MLP4Rec. Extensive experimental results demonstrate that the proposed method is significantly superior to the state-of-the-art approaches. The implementation code is available online to ease reproducibility.

Over the last few years, sequential recommender systems have achieved a great success in different applications. In the literature, it is generally believed that items farther away from the recommendation time have a weaker impact on the recommendation results. However, simply considering the distance between the interaction time and the recommendation time would prevent effective user representations. To solve this issue, we propose a Time Interval Aware Collaborative (TIAC) model with self-supervised learning for sequential recommendation. We propose to adjust the attention score learned from the time interval between an interaction time and the recommendation time using a time kernel function to achieve a better user representation. We also introduce self-supervised learning to combine the collaborative information obtained from a graph convolutional network and the sequential information learned from gated recurrent units to further enrich user representation. Extensive experiments on four real-world benchmark datasets show that our proposed TIAC model consistently outperforms state-of-the-art models under various evaluation metrics.KeywordsSequential recommendationAttention mechanismSelf-supervised learningGraph convolutional network

Recommending events to groups is different from to single-user in event-based social networks (EBSN), which involves various complex factors. Generally, group recommendation methods are either based on recommendation fusion or model fusion. However, most existing methods neglect the fact that user preferences change over time. Moreover, they believe that the weights of different factors that affect group decision-making are fixed in different periods. Recently, there are a few works using the attention mechanism for group recommendation. Although they take into account the dynamic variability of user preferences and the dynamic adjustment of user features weights, they haven’t discussed more features of groups and events affecting group decision-making. To this end, we propose a novel Feature-level Hierarchical Attention Network (FHAN) for group event recommendation for EBSN. Specifically, group decision-making factors are divided into group-feature factors and event-feature factors, which are integrated into a two-layer attention network. The first attention layer is constructed to learn the influence weights of words of group topics and event topics, which generates better thematic features. The second attention layer is built to learn the weights of group-feature factors and event-feature factors affecting group decision-making, which results in better comprehensive representation of groups and events. All influence weights of different features in the model can be dynamically adjusted over time. Finally, we evaluate the suggested model on three real-world datasets. Extensive experimental results show that FHAN outperforms the state-of-the-art approaches.

Sequential recommendation effectively addresses information overload by modeling users' temporal and sequential interaction patterns. To overcome the limitations of supervision signals, recent approaches have adopted self-supervised learning techniques in recommender systems. However, there are still two critical challenges that remain unsolved. Firstly, existing sequential models primarily focus on long-term modeling of individual interaction sequences, overlooking the valuable short-term collaborative relationships among the behaviors of different users. Secondly, real-world data often contain noise, particularly in users' short-term behaviors, which can arise from temporary intents or misclicks. Such noise negatively impacts the accuracy of both graph and sequence models, further complicating the modeling process. To address these challenges, we propose a novel framework called Self-Supervised Graph Neural Network (SelfGNN) for sequential recommendation. The SelfGNN framework encodes short-term graphs based on time intervals and utilizes Graph Neural Networks (GNNs) to learn short-term collaborative relationships. It captures long-term user and item representations at multiple granularity levels through interval fusion and dynamic behavior modeling. Importantly, our personalized self-augmented learning structure enhances model robustness by mitigating noise in short-term graphs based on long-term user interests and personal stability. Extensive experiments conducted on four real-world datasets demonstrate that SelfGNN outperforms various state-of-the-art baselines. Our model implementation codes are available at https://github.com/HKUDS/SelfGNN.

Sequential recommendation aims to capture users' dynamic interest and predicts the next item of users' preference. Most sequential recommendation methods use a deep neural network as sequence encoder to generate user and item representations. Existing works mainly center upon designing a stronger sequence encoder. However, few attempts have been made with training an ensemble of networks as sequence encoders, which is more powerful than a single network because an ensemble of parallel networks can yield diverse prediction results and hence better accuracy. In this paper, we present Ensemble Modeling with contrastive Knowledge Distillation for sequential recommendation (EMKD). Our framework adopts multiple parallel networks as an ensemble of sequence encoders and recommends items based on the output distributions of all these networks. To facilitate knowledge transfer between parallel networks, we propose a novel contrastive knowledge distillation approach, which performs knowledge transfer from the representation level via Intra-network Contrastive Learning (ICL) and Cross-network Contrastive Learning (CCL), as well as Knowledge Distillation (KD) from the logits level via minimizing the Kullback-Leibler divergence between the output distributions of the teacher network and the student network. To leverage contextual information, we train the primary masked item prediction task alongside the auxiliary attribute prediction task as a multi-task learning scheme. Extensive experiments on public benchmark datasets show that EMKD achieves a significant improvement compared with the state-of-the-art methods. Besides, we demonstrate that our ensemble method is a generalized approach that can also improve the performance of other sequential recommenders. Our code is available at this link: https://github.com/hw-du/EMKD.

Simple Debiased Contrastive Learning for Sequential Recommendation

A POI group recommendation method in location-based social networks based on user influence

KTPGN: Novel event-based group recommendation method considering implicit social trust and knowledge propagation

Knowledge graph has been widely utilized to provide knowledge for the sequential recommendation. But their divergence produces new challenges to appropriately capture and represent items’ knowledge for recommendation. Additionally, the complex temporal features also increase the difficulty to model the user-item interaction sequences. The key issues remaining to be settled are how to mine adequate information from KG to capture items’ knowledge, and how to model the evolving user interests accurately. Facing the above problems, we propose a multi-task learning framework MLKT to learn the embedding of items and users’ dynamic preferences in both a knowledge-aware and time-aware way. Different from the previous works, we not only consider the timestamps of the interactions in the sequence, but also capture its evolution from multiple perspectives by designing a multi-scale temporal attention mechanism. Additionally, we represent each item’s features in different granularity by learning from neighbors and the category information in KG. Furthermore, to make the KG embeddings to be more suitable for the recommendation, a cross-component is designed to efficiently achieve the item information communication between KG and user-item interactions. Extensive experiments demonstrate the significant improvements of MLKT than the baseline methods on two recommendation tasks in three datasets.

Sequential recommendation (SR) aims to predict the subsequent behaviors of users by understanding their successive historical behaviors. Recently, some methods for SR are devoted to alleviating the data sparsity problem (i.e., limited supervised signals for training), which take account of contrastive learning to incorporate self-supervised signals into SR. Despite their achievements, it is far from enough to learn informative user/item embeddings due to the inadequacy modeling of complex collaborative information and co-action information, such as user-item relation, user-user relation, and item-item relation. In this paper, we study the problem of SR and propose a novel multi-level contrastive learning framework for sequential recommendation, named MCLSR. Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i.e., interest- and feature-level). Specifically, the interest-level contrastive mechanism jointly learns the collaborative information with the sequential transition patterns, and the feature-level contrastive mechanism re-observes the relation between users and items via capturing the co-action information (i.e., co-occurrence). Extensive experiments on four real-world datasets show that the proposed MCLSR outperforms the state-of-the-art methods consistently.

Group recommendation has attracted significant research efforts for its importance in benefiting a group of users. This paper investigates the Group Recommendation problem from a novel aspect, which tries to maximize the satisfaction of each group member while minimizing the unfairness between them. In this work, we present several semantics of the individual utility and propose two concepts of social welfare and fairness for modeling the overall utilities and the balance between group members. We formulate the problem as a multiple objective optimization problem and show that it is NP-Hard in different semantics. Given the multiple-objective nature of fairness-aware group recommendation problem, we provide an optimization framework for fairness-aware group recommendation from the perspective of Pareto Efficiency. We conduct extensive experiments on real-world datasets and evaluate our algorithm in terms of standard accuracy metrics. The results indicate that our algorithm achieves superior performances and considering fairness in group recommendation can enhance the recommendation accuracy.