Sequential recommendation aims to predict users’ next actions by modeling temporal dependencies in interaction sequences. However, existing attention- or graph-based models often struggle to jointly capture hierarchical semantics, long-range dependencies, and multi-relational knowledge, leading to suboptimal performance in sparse and cold-start scenarios. In this article, we propose KHARec, a knowledge-enhanced hyperbolic attention network that unifies geometric representation learning and temporal modeling for trustworthy sequential recommendation. KHARec consists of a hyperbolic fine-grain module that encodes hierarchical semantics from knowledge graphs, a Transformer-based coarse-grain module that models global dependencies with an FFT-based filter, and a learnable gating mechanism for adaptive feature fusion. Extensive experiments on three benchmark datasets demonstrate that KHARec consistently outperforms state-of-the-art sequential and knowledge-aware baselines in terms of HR@K and NDCG@K, while maintaining near-linear computational complexity. Further analyses verify the model’s robustness under sparsity and cold-start conditions and its superior capability in handling long-tail items. Overall, KHARec provides an interpretable and efficient framework for integrating hyperbolic reasoning and attention-based sequence modeling in large-scale recommendation environments.

Recent years have seen rapid progress in network representation learning, which removes the need for burdensome feature engineering and facilitates downstream network-based tasks. In reality, networks often exhibit heterogeneity, which means there may exist multiple types of nodes and interactions. Heterogeneous networks raise new challenges to representation learning, as the awareness of node and edge types is required. In this article, we study a basic building block of general heterogeneous networks, the heterogeneous networks with two types of nodes. Many problems can be solved by decomposing general heterogeneous networks into multiple bipartite ones. Recently, to overcome the demerits of non-metric measures used in the embedding space, metric learning-based approaches have been leveraged to tackle heterogeneous network representation learning. These approaches first generate triplets of samples, in which an anchor node, a positive counterpart, and a negative one co-exist, and then try to pull closer positive samples and push away negative ones. However, when dealing with heterogeneous networks, even the simplest two-typed ones, triplets cannot simultaneously involve both positive and negative samples from different parts of networks. To address this incompatibility of triplet-based metric learning, in this article, we propose a novel quintuple-based method for learning node representations in bipartite heterogeneous networks. Specifically, we generate quintuples that contain positive and negative samples from two different parts of networks. And we formulate two learning objectives that accommodate quintuple-based learning samples, a proximity-based loss that models the relations in quintuples by sigmoid probabilities and an angular loss that more robustly maintains similarity structures. In addition, we also parameterize feature learning by using one-dimensional convolution operators around nodes’ neighborhoods. Compared with eight methods, extensive experiments on two downstream tasks manifest the effectiveness of our approach.

Exploring user-item interaction cues is crucial for the performance of recommender systems. Explicit investigation of interaction cues is made possible by using graph-based models, where each user-item relationship is described by an edge, and the introduction of user-user social network. While existing graph-based recommendation methods use only a single-value edge to define the relationship between a pair of user and item, which limits the ability to represent complex user-item interactions. Furthermore, some social recommendation methods overlook the heterogeneous user behavior patterns in social and interaction relationships, resulting in the suboptimal performance of existing systems. In this paper, we propose a novel Social-aware Multi-dimensional Edge Feature-based Graph Representation Learning method, called SMEF. It represents all users and items as a graph and deep learns a multi-dimensional edge feature to explicitly describe the task-specific relationships of each user-item pair. Specifically, the proposed SMEF focuses on two distinct user behavior patterns toward social friends and interactive items, which explore the underlying heterogeneous relationship cues within them. This way, the learned multi-dimensional edge features encode user information from both social and interaction aspects. The proposed SMEF is a plug-and-play module that can be combined with different recommendation frameworks and Graph Neural Networks (GNNs) backbones to generate high quality user representations. The experimental results achieved on three publicly accessible datasets show that our SMEF-based method outperforms strong baselines.

In image, video and even real physics domains, adversarial examples can mislead deep models to produce wrong predictions. Transfer-based attacks against black-box models are more in line with realistic scenarios, but adversarial examples made on surrogate model have a low success rate when transferred to the target model due to overfitting the source model. We study the Stochastic Weight Averaging strategy in the domain generalization process and propose a Stochastic Perturbation Averaging method (SPA). Specifically, we add stochastic perturbations to the examples during the gradient descent attack, and we design a Central Amplification method (CAM) to enhance this random variation, then SPA stabilizes the iteration direction by computing the gradient average of the perturbed examples to find a relatively flat local minimum of the loss function. SPA is an efficient and general strategy which can significantly improve the transferability of the gradient-based attack methods. For instance, the average attack success rate of the adversarial examples produced based on four single models against seven pre-trained models reached 90.10%, which is the best result so far. Code is available at https://github.con yangrongbo/SPA.

In recent years, the field of unsupervised graph representation learning has witnessed the emergence of graph contrastive learning (GCL) as a highly successful approach. GCL excels in learning graph representations by effectively bringing positive sample pairs into proximity while simultaneously pushing negative sample pairs apart in the representation space, without any manual labels. Graph-structured data to be learned inherently exhibits a critical hierarchical structure, which is crucial for organizing and managing graphs. Leveraging this attribute enhances the accuracy of graph representation outcomes. However, current GCL methods tend to overlook the hierarchical structure, which can result in sampling bias during node selection. Nodes of the same semantics can potentially be sampled as negative pairs. To overcome these limitations, we present a novel framework, Hierarchical Graph Contrastive Learning via Debiasing Noise Samples with Adaptive Repelling Ratio (HGClear). Our framework enables the simultaneous learning of node representations and the graph hierarchy in an end-to-end manner. During the process of method design, we discovered that the accuracy of node category prediction significantly affects representation results. To remove the bias caused by noise samples, we introduced a module to handle boundary nodes (i.e., noise samples) that are vulnerable to mislabeling. Specifically, we introduce a hierarchy detection module that captures both coarse-grained views and category attributes of nodes. Leveraging these results, we can identify boundary nodes and establish varying repelling ratios based on category labels, replacing the conventional temperature coefficient in the contrastive loss. Simultaneously incorporating an intra-view node contrast module not only eliminates the bias resulting from noise samples but also enhances the uniqueness of node representations. Numerous experiments on node classification datasets show that HGClear produces encouraging results and outperforms some state-of-the-art methods.

The application of recommendation systems online services is becoming more and more extensive. However, most existing recommendation algorithms centralize multi-party information into a central processor, which may lead to the risk of privacy leakage. And many enterprises or institutions still have the problem that data cannot be shared. Federated learning has been introduced into recommendation algorithms for privacy- aware distributed learning. A typical federated learning is that each client uses local data to train a shared model, the server uses their gradient information to form a global model, and then each client updates. In this paper, we propose a federated deep recommendation algorithm called FedHe-mlp that applies a federated deep learning for data privacy protection, and combines heterogeneous information network (HIN) and matrix factorization technique for better prediction performance. First, each client obtains heterogeneous information through meta- paths, then we combine matrix factorization and heterogeneous information to mine the latent features and heterogeneous features of each client. Finally, We propose a deep neural network that considers features from multiple views. Extensive experiments on three public datasets demonstrate that FedHe- mlp can provide excellent convergence speed, recommendation accuracy, and communication efficiency while preserving data privacy.

Real-world networks often show heterogeneity. A frequently encountered type is the bipartite heterogeneous structure, in which two types of nodes and three types of edges exist. Recently, much attention has been devoted to representation learning in these networks. One of the essential differences between heterogeneous and homogeneous learning is that the former structure requires methods to possess awareness to node and edge types. Most existing methods, including metapath-based, proximity-based and graph neural network-based, adopt inner product or vector norms to evaluate the similarities in embedding space. However, these measures either violates the triangle inequality, or show severe sensitivity to scaling transformation. The limitations often hinder the applicability to real-world problems. In view of this, in this paper, we propose a novel angle-based method for bipartite heterogeneous network representation. Specifically, we first construct training sets by generating quintuples, which contain both positive and negative samples from two different parts of networks. Then we analyze the quintuple-based problem from a geometry perspective, and transform the comparisons between preferred and non-preferred samples to the comparisons of angles. In addition, we utilize convolution modules to extract node features. A hinge loss, as the final objective, is proposed to relax the angular constraint for learning. Extensive experiments for two typical tasks show the efficacy of the proposed method, comparing with eight competitive methods.

Keyphrase annotation task aims to retrieve the most representative phrases that express the essential gist of documents. In reality, some phrases that best summarize documents are often absent from the original text, which motivates researchers to develop generation methods, being able to create phrases. Existing generation approaches usually adopt the encoder-decoder framework for sequence generation. However, the widely-used recurrent neural network might fail to capture long-range dependencies among items. In addition, intuitively, as keyphrases are likely to correlate with topical words, some methods propose to introduce topic models into keyphrase generation. But they hardly leverage the global information of topics. In view of this, we employ the Transformer architecture with the pre-trained BERT model as the encoder-decoder framework for keyphrase generation. BERT and Transformer are demonstrated to be effective for many text mining tasks. But they have not been extensively studied for keyphrase generation. Furthermore, we propose a topic attention mechanism to utilize the corpus-level topic information globally for keyphrase generation. Specifically, we propose BertTKG, a keyphrase generation method that uses a contextualized neural topic model for corpus-level topic representation learning, and then enhances the document representations learned by pre-trained language model for better keyphrase decoding. Extensive experiments conducted on three public datasets manifest the superiority of BertTKG.

Bag-of-words (BOW) is now the most popular way to model text in statistical machine learning approaches in sentiment analysis. However, the performance of BOW sometimes remains limited due to some fundamental deficiencies in handling the polarity shift problem. We propose a model called dual sentiment analysis (DSA), to address this problem for sentiment classification. We first propose a novel data expansion technique by creating a sentiment-reversed review for each training and test review. On this basis, we propose a dual training algorithm to make use of original and reversed training reviews in pairs for learning a sentiment classifier, and a dual prediction algorithm to classify the test reviews by considering two sides of one review. We also extend the DSA framework from polarity (positive-negative) classification to 3-class (positive-negative-neutral) classification, by taking the neutral reviews into consideration. Finally, we develop a corpus-based method to construct a pseudo-antonym dictionary, which removes DSA's dependency on an external antonym dictionary for review reversion. We conduct a wide range of experiments including two tasks, nine datasets, two antonym dictionaries, three classification algorithms, and two types of features. The results demonstrate the effectiveness of DSA in supervised sentiment classification.