Search

Sequential Recommendation (SR) methods play a crucial role in recommender systems, which aims to capture users’ dynamic interest from their historical interactions. Recently, Contrastive Learning (CL), which has emerged as a successful method for sequential recommendation, utilizes various data augmentations to generate contrastive views to mine supervised signals from data to alleviate data sparsity issues. However, most existing sequential data augmentation methods may destroy semantic sequential interaction characteristics. Meanwhile, they often adopt random operations when generating contrastive views leading to suboptimal performance. To this end, in this paper, we propose a Learnable Model Augmentation Contrastive learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes the model-based augmentation method to generate constructive views. Then, LMA4Rec uses Learnable Bernoulli Dropout (LBD) to implement learnable model augmentation operations. Next, contrastive learning is used between the contrastive views to extract supervised signals. Furthermore, a novel multi-positive contrastive learning loss alleviates the supervised sparsity issue. Finally, experiments on public datasets show that our LMA4Rec method effectively improved sequential recommendation performance compared with the state-of-the-art baseline methods.

Graph Pattern based Node Matching (GPNM) is to find all the matches of the nodes in a data graph $G_D$GD based on a given pattern graph $G_P$GP. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both $G_P$GP and $G_D$GD are updated frequently. However, the existing GPNM methods either need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated $G_P$GP and $G_D$GD or incrementally perform the GPNM procedure for each of the updates, leading to low efficiency. Although the elimination relations between updates and partitions of data graphs are considered in the state-of-the-art method, it still suffers from low efficiency as only the labels of nodes are considered in the partitions. Therefore, there is a pressing need for a new method to efficiently deliver the node matching results on the updated graphs. In this paper, we propose a new Partition-aware GPNM algorithm, called P-GPNM, where we propose two new partition methods, i.e., connection-based partition and density-based partition. In these two methods, P-GPNM considers the dense connections between partitions and the inner connections inside a single partition, respectively. The experimental results on five real-world social graphs demonstrate that our proposed P-GPNM is much more efficient than the state-of-the-art GPNM methods.

Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) have been proposed to improve the recommendation accuracy in a target dataset (domain/system) with the help of a source one with relatively richer information. However, most existing CDR and CSR approaches are single-target, namely, there is a single target dataset, which can only help the target dataset and thus cannot benefit the source dataset. In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all scenarios. To do this, we propose a unified framework, called GA (based on Graph embedding and Attention techniques), for all three scenarios. In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common entities (users/items) learned from different datasets. Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i.e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively. Extensive experiments conducted on four real-world datasets demonstrate that our proposed GA models significantly outperform the state-of-the-art approaches.

An attributed dynamic graph contains multiple dynamic attributes associated with each edge in the graph. In attributed dynamic graph based applications, people usually can specify multiple constraints in the attributes to illustrate their requirements, such as the total cost, the total travel time and the stopover interval of a flight between two cities. This inspires the multi-constrained temporal path discovery in attributed dynamic graphs, which is a challenging NP-complete problem. To solve the problem, the existing methods adopt reinforcement learning with Monte Carlo tree search. However, these reinforcement learning based methods require a certain degree of “discovery experience” to obtain better results, which can lead to the expensive cost of query time and storage space, and thus are not applicable in real-time applications, e.g., route recommendations in a self-driving car. This motivates us to develop a new Adaptive Monte Carlo Tree Search algorithm, namely A-MCTS. A-MCTS dynamically adjusts the priority of historical records that are used in Monte Carlo tree search to improve the performance and reduce the size of required “discovery experience”. In addition, A-MCTS proposes a new adaptive replay memory structure that can store important historical records based on graph properties and optimize the consumption of storage space. The experimental results on ten real-world dynamic graphs demonstrate that the proposed A-MCTS outperforms the state-of-the-art methods in terms of both efficiency and effectiveness.