Collaborative Filtering (CF) with implicit feedback is widely used in personalized recommender systems. In most real-world scenarios, only implicit feedback signals are available, making CF training heavily dependent on sampling-based paradigms—typically optimized via pairwise ranking losses such as Bayesian Personalized Ranking (BPR). This simple yet effective approach has achieved remarkable success and remains the foundation of many modern recommender models. However, despite its empirical success, little attention has been paid to the inherent training instability issue under this sampling-based paradigm. In this paper, we conduct an in-depth analysis of training stability and find that unstable training not only hinders convergence but also leads to fluctuating and suboptimal recommendation performance. We identify two fundamental sources of this instability in CF: (1) noisy or sparse positive samples, where a single observed interaction may not reliably reflect user preference; and (2) inconsistent negative samples, where randomly drawn negatives from unobserved space vary drastically in negative hardness, leading to uninformative or noisy gradient updates. To address these two challenges, we propose StabCF, a Stabilized Training Method for Collaborative Filtering, which improves training stability by synthesizing enriched positive samples from historical positives and constructing consistent hard negatives through user-aware negatives mixing. By replacing raw training triplets with synthesized positive-negative pairs, StabCF effectively smooths the training dynamics and improves convergence stability. Extensive experiments on three public datasets demonstrate that StabCF not only significantly stabilizes the training process but also achieves superior recommendation performance. Our PyTorch implementation is available at https://github.com/Wu-Xi/StabCF.

Negative sampling plays a pivotal role in training recommendation systems with implicit feedback, where the effectiveness of negatives directly impacts model convergence and recommendation quality. The key challenge is to efficiently mine high-quality hard negatives from the massive item space. Existing strategies typically rely on a single user perspective as the sampling anchor and use discrete arg max operations to select negatives. However, the single-anchor design introduces noisy negatives, and the discrete hard selection prevents end-to-end optimization. To address these limitations, we propose a differentiable dual-anchor negative sampling framework for graph-based recommendation. Our framework introduces a differentiable cross-hop sampling mechanism based on the Gumbel-Softmax trick, enabling hard negative selection while preserving gradient flow. Furthermore, we incorporate both the user and the corresponding positive item as complementary sampling anchors to improve the quality and stability of negative samples. Extensive experiments on three benchmark datasets demonstrate that our approach consistently improves recommendation performance.

Negative sampling plays a critical role in collaborative filtering (CF), as it accelerates convergence and improves recommendation accuracy. Among recent studies, mixup-based negative sampling has shown promising performance. However, existing methods primarily focus on increasing the similarity between the synthesized negative and the positive item, without considering the false positive issue commonly found in implicit feedback scenarios. Blindly training all positive samples with overly hard negatives can magnify the impact of false positives and hurt recommendation performance. To address this challenge, we first provide a theoretical analysis revealing that mixup-synthesized hard negatives implicitly reweight the similarity difference between the user's interactions and both the positive and negative boundaries, thereby shaping the training signal. Motivated by this, we propose a novel strategy named Dual Context-Aware Negative Sampling (DCANS), which enhances each positive item by assessing its alignment with the user's interest context, and simultaneously adjusts the hardness of synthesized negatives based on their relevance to the same interest context. This strategy optimizes the training direction toward the user's genuine preferences, mitigating the negative impact of false positives while preserving the benefits of hard negative sampling. Extensive experiments on three benchmark datasets demonstrate that our method achieves consistent improvements over state-of-the-art baselines. Our PyTorch implementation is available https://github.com/Wu-Xi/DCANS.

Currently, many researchers aim to achieve automatic depression level prediction via speech and video behavior analysis. However, previous works have struggled to decompose audio and video sequences into the information related to and unrelated to depression scores, hindering the model’s perception of depression cues. Besides, previous works implement multimodal fusion using attention mechanisms or linear layers, but failed to simultaneously consider the Euclidean relationship among tokens and the non-Euclidean relationship among channels, which bring limitations in capturing depression cues. In response to the above issues, we propose a depression scale dictionary decomposition framework, which mainly includes a Bidirectional Dictionary Decomposition (BDD) module and a Bidirectional Multimodal Fusion (BMF) module. The BDD module can use the dictionaries generated based on the depression scale to semantically decompose audio and video sequences into the information related to and unrelated to depression scores along token and channel dimensions for promoting depression cue perception. Moreover, considering the respective characteristics of tokens and channels, the BMF module uses linear layers and graph convolution to achieve cross-modal mixing, which is used to aggregate audio and video sequences for predicting depression levels. The validation on AVEC 2013, AVEC 2014 and DAIC-WOZ datasets demonstrates our method’s superiority.

Graph neural networks (GNNs) are commonly used and have shown promising performance in recommendation systems. A major branch, heterogeneous GNNs, models heterogeneous information by leveraging side information for academic paper recommendations. These networks use message passing and high-order propagation to learn representations for users and items. However, existing recommendation methods perform high-order propagation, leading to sub-optimal representation learning. To address this issue, this article proposes a framework called MCAP, which uses relation-aware GNNs and executes low-pass propagation with matrix completion to enhance academic paper recommendations. The framework uses an attention mechanism to learn top- \(U\) relationships by constructing a user–user relation graph based on common authors and venues from interacted items. To efficiently and effectively capture semantic-aware similar items, MCAP builds an item–item relation graph by fusing side information of papers using text embedding models (e.g., Mistral) and large language models (e.g., GPT-3.5-Turbo, GLM-4). Finally, the relation-aware user–user and item–item graphs are incorporated into existing GNN-based models to generate representations of users and papers to enhance academic paper recommendations. The effectiveness of the MCAP is validated using four academic datasets, AMiner-PC, AMiner-WeChat, CiteULike, and DBLP, with user–item interactions and side information of papers. Comprehensive experiments show that the MCAP outperforms state-of-the-art models in terms of Recall@5, NDCG@5, and HR@5 with 69.2%, 70.5%, and 77.6% on the AMiner-WeChat dataset. The code for MCAP is available at https://github.com/THUDM/MCAP .

The knowledge graph (KG) enhanced recommendation system has shown superior performance and attracted considerable attention. In recent years, researchers have attempted to apply graph neural networks (GNNs) and build end-to-end knowledge graph enhanced recommendation systems. Although several methods are proposed, it is still challenging to apply GNNs to solve the problem of KG enhanced recommendation due to the heterogeneous, redundant, and large-scale nature of KG versus the homogeneous nature of GNNs. To address the limitations of existing techniques, we propose a transformed heterogeneous graph neural network (TRANSGNN), an item-centric and GNN-powered framework that can better explore the heterogeneous, redundant, and large-scale relations among items in KG for an effective and efficient KG enhanced top- K recommendation. In particular, we propose an item-centric graph transformation module to transform the heterogeneous KG into a homogeneous item-item graph. This scheme allows us to distill the knowledge from the KG and encode the heterogeneous, redundant, and large-scale item-item relationship into a smaller, compact, homogeneous graph, better fitting the GNNs architecture that prefers homogeneous and small-scale graph input. We further introduce a collaborative graph fusion module to fuse the item-wise KG relational signals and the collaborative signals by augmenting the collaborative graph with the transformed item-item graph. Next, we propose to use a graph collaborative encoder over the augmented graph to propagate information along with high-order connectivity. The proposed framework is general and can be easily extended with advanced KG embedding and GNN models. Extensive experiments on three public datasets demonstrate the effectiveness of the proposed approach in significantly (up to 23%) improving the KG enhanced recommendation performance over the state-of-the-art methods, such as KGIN, KGAT, KGNN-LS in both regular and cold-start settings. The proposed approach is also efficient with significantly (up to 31%) fewer parameters.

Collaborative filtering (CF) is a widely employed technique that predicts user preferences based on past interactions. Negative sampling plays a vital role in training CF-based models with implicit feedback. In this paper, we propose a novel perspective based on the sampling area to revisit existing sampling methods. We point out that current sampling methods mainly focus on Point-wise or Line-wise sampling, lacking flexibility and leaving a significant portion of the hard sampling area un-explored. To address this limitation, we propose Dimension Independent Mixup for Hard Negative Sampling (DINS), which is the first Area-wise sampling method for training CF-based models. DINS comprises three modules: Hard Boundary Definition, Dimension Independent Mixup, and Multi-hop Pooling. Experiments with real-world datasets on both matrix factorization and graph-based models demonstrate that DINS outperforms other negative sampling methods, establishing its effectiveness and superiority. Our work contributes a new perspective, introduces Area-wise sampling, and presents DINS as a novel approach that achieves state-of-the-art performance for negative sampling. Our implementations are available in PyTorch.

Vision transformers have significantly advanced the field of computer vision in recent years. The cornerstone of these transformers is the multi-head attention mechanism, which models interactions between visual elements within a feature map. However, the vanilla multi-head attention paradigm independently learns parameters for each head, which ignores crucial interactions across different attention heads and may result in redundancy and under-utilization of the model’s capacity. To enhance model expressiveness, we propose a novel nested attention mechanism, Ne-Att, that explicitly models cross-head interactions via a hierarchical variational distribution. We conducted extensive experiments on image classification, and the results demonstrate the superiority of Ne-Att.

Cross-Domain Recommendation (CDR) is capable of incorporating auxiliary information from multiple domains to advance recommendation performance. Conventional CDR methods primarily rely on overlapping users, whereby knowledge is conveyed between the source and target identities belonging to the same natural person. However, such a heuristic assumption is not universally applicable due to an individual may exhibit distinct or even conflicting preferences in different domains, leading to potential noises. In this paper, we view the anchor links between users of various domains as the learnable parameters to learn the task-relevant cross-domain correlations. A novel optimal transport based model ALCDR is further proposed to precisely infer the anchor links and deeply aggregate collaborative signals from the perspectives of intra-domain and inter-domain. Our proposal is extensively evaluated over real-world datasets, and experimental results demonstrate its superiority.

We propose a self-supervised embedding learning frameworkSelfLinKGto link concepts in heterogeneous knowledge graphs. Without any labeled data, SelfLinKG can achieve competitive performance against its supervised counterpart, and significantly outperforms state-of-the-art unsupervised methods by 26%-50%. The essential components of SelfLinKG are local attention-based encoding and momentum contrastive learning. The former aims to learn the graph representation using an attention network, while the latter is to learn a self-supervised model across knowledge graphs using contrastive learning. SelfLinKG has been deployed to build the the new version, called OAG_know of Open Academic Graph (OAG). All data and codes are publicly available.

Massive open online courses (MOOCs), which offer open access and widespread interactive participation through the internet, are quickly becoming the preferred method for online and remote learning. Several MOOC platforms offer the service of course recommendation to users, to improve the learning experience of users. Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise. To mitigate this gap, we examine an interesting problem of concept recommendation in this paper, which can be viewed as recommending knowledge to users in a fine-grained way. We put forward a novel approach, termedHinCRec-RL, forConceptRecommendation in MOOCs, which is based onHeterogeneousInformationNetworks andReinforcementLearning. In particular, we propose to shape the problem of concept recommendation within a reinforcement learning framework to characterize the dynamic interaction between users and knowledge concepts in MOOCs. Furthermore, we propose to form the interactions among users, courses, videos, and concepts into aheterogeneous information network (HIN)to learn the semantic user representations better. We then employ an attentional graph neural network to represent the users in the HIN, based on meta-paths. Extensive experiments are conducted on a real-world dataset collected from a Chinese MOOC platform,XuetangX, to validate the efficacy of our proposed HinCRec-RL. Experimental results and analysis demonstrate that our proposed HinCRec-RL performs well when compared with several state-of-the-art models.

Knowledge graph (KG) enhanced recommendation has demonstrated improved performance in the recommendation system (RecSys) and attracted considerable research interest. Recently the literature has adopted neural graph networks (GNNs) on the collaborative knowledge graph and built an end-to-end KG-enhanced RecSys. However, the majority of these approaches have three limitations: (1) treat the collaborative knowledge graph as a homogeneous graph and overlook the highly heterogeneous relationships among items, (2) lack of design to explicitly leverage the rich side information, and (3) overlook the rich knowledge in user preference.To fill this gap, in this paper, we explore the rich, heterogeneous relationship among items and propose a new KG-enhanced recommendation model called Collaborative Meta-Knowledge Enhanced Recommender System (MetaKRec). In particular, we focus on modeling the rich, heterogeneous semantic relationships among items and construct several collaborative Meta-KGs to explicitly depict the relatedness of the items under the guidance of meta-knowledge. In addition to the knowledge obtained from KG, we leverage user knowledge that extracts from user preference to construct the Meta-KGs. The constructed Meta-KGs can capture the knowledge from both the knowledge graph and user preference. Furthermore. we utilize a light convolution encoder to recursively integrate the item relationship in each collaborative Meta-KGs. This scheme allows us to explicitly gather the heterogeneous semantic relationships among items and encode them into the representations of items. In addition, we propose channel attention to fuse the item and user representations from different Meta-KGs. Extensive experiments are conducted on four real-world benchmark datasets, demonstrating significant gains over the state-of-the-art baselines on both regular and cold-start recommendation settings.

As a hot topic in computer vision, target tracking has a vital application in many scientific and technological fields. The tracking method based on correlation filtering transforms the target tracking from the time domain to the frequency domain through the Fourier transform, which can boost the accuracy and success rate. However, in the complex tracking environments, the target tracking process may be affected by deformation, occlusion, and other inferences, which make the traditional target tracking algorithms hardly accommodate the requirements of robustness. Aiming the target tracking in complex scenes, this paper tries to improve the feature extraction based on the Convolution Neural Network, which can learn deep features of the target from different convolution layers with more abstract characteristics. Then these multiple features are fused to enhance the robustness performance of the traditional Kernel Correlation Filter algorithm from the aspects of model characteristics. Furthermore, the accuracy and success rate of the proposed algorithm are verified based on comprehensive comparative experiments in the Object Tracking Benchmark with variant interferences.

Massive open online courses (MOOCs) are becoming a modish way for education, which provides a large-scale and open-access learning opportunity for students to grasp the knowledge. To attract students' interest, the recommendation system is applied by MOOCs providers to recommend courses to students. However, as a course usually consists of a number of video lectures, with each one covering some specific knowledge concepts, directly recommending courses overlook students' interest to some specific knowledge concepts. To fill this gap, in this paper, we study the problem of knowledge concept recommendation. We propose an end-to-end graph neural network based approach calledAttentional Heterogeneous Graph Convolutional Deep Knowledge Recommender (ACKRec) for knowledge concept recommendation in MOOCs. Like other recommendation problems, it suffers from sparsity issue. To address this issue, we leverage both content information and context information to learn the representation of entities via graph convolution network. In addition to students and knowledge concepts, we consider other types of entities (e.g., courses, videos, teachers) and construct a heterogeneous information network (HIN) to capture the corresponding fruitful semantic relationships among different types of entities and incorporate them into the representation learning process. Specifically, we use meta-path on the HIN to guide the propagation of students' preferences. With the help of these meta-paths, the students' preference distribution with respect to a candidate knowledge concept can be captured. Furthermore, we propose an attention mechanism to adaptively fuse the context information from different meta-paths, in order to capture the different interests of different students. To learn the parameters of the proposed model, we propose to utilize extended matrix factorization (MF). A series of experiments are conducted, demonstrating the effectiveness of ACKRec across multiple popular metrics compared with state-of-the-art baseline methods. The promising results show that the proposed ACKRec is able to effectively recommend knowledge concepts to students pursuing online learning in MOOCs.

Pulse Diagnosis Theory (PDT) has the advantages of non-invasive treatment and disease prevention. Combining these merits with Wireless Sensor Network(WSN), we propose a novel networked low-cost and wearable healthcare monitoring system, namely PDhms, for pulse data collection, pulse analysis and pulse diagnosis. Some practical challenges still exist in PDhms such as exerting appropriate pressure on a human radial artery, overcoming seriously limited resources, improving low Signal to Noise Ratio(SNR) and conducting resistance of interference. To address these challenges, we present a robust external pressure control algorithm for pulse data collection, and propose FEA, a novel light-weight and adaptive feature extraction algorithm for sensed pulse data. We conduct the large-scale pulse data collection experiments of 1356 pulse samples, the comparison experiment between the FEA and the typical derivative-based algorithm, as well as pulse diagnosis experiments based on SVM. Experimental results show that PDhms is a valuable solution for low-cost wearable healthcare monitoring system. It will benefit the public, especially low-income groups because small pulse-sensor node size, low system cost, as well as wearable pulse data collection and analysis.

Traditional Chinese Pulse Diagnosis is a convenient and noninvasive method for disease diagnosis and healthcare. We have designed and implemented a Chinese wrist-pulse retrieval system based on the principle of Traditional Chinese Pulse Diagnosis (TCPD), called EasiCPRS. It is designed to be small in size, low in cost, with flexibility in deployment, and simplicity in operation. The contributions of this work are: 1. The wrist-pulse at "cun, guan and chi"points over the radial artery are obtained by applying a moderate and adjustable taking pressure during wrist-pulse retrieval. 2. A wrist-pulse signal conditioning circuit and a robust external taking pressure control algorithm are designed to overcome low signal-to-noise ratio (SNR). 3. A lightweight algorithm for wrist-pulse feature extraction is achieved on a resource-constrained platform to economize energy and bandwidth.

Traffic information acquisition is often implemented by video cameras or inductive loops, which is expensive or inconvenient from installation and maintenance perspectives. We designed and implemented a pervasive traffic information acquisition system based on wireless sensor networks called EasiTia. Unlike existing solutions, the implementation of the system does not require extra devices in the road infrastructure or vehicle, nor the excavation of the road surfaces. EasiTia can easily be deployed at roadsides. It is of low cost and resource efficient. Our contributions are given as follows: 1) To deal with low signal-to-noise ratios (SNRs) and stochastic disturbances in traffic information acquisition, we proposed and implemented a cross-correlation-based vehicle-detection algorithm. 2) To resolve the problems of data association, vehicle velocity calculation, and vehicle identification, we proposed a collaborative traffic information processing mechanism in the EasiTia system. Based on real road environment experimental analysis, we demonstrate that EasiTia is an applicable and cost-effective candidate for a pervasive traffic information acquisition system.

To meet the increasing needs of home-based healthcare, we propose a novel networked low-cost and wearable healthcare monitoring system, namely TCM-PCA, for pulse analysis in Traditional Chinese Medicine(TCM). The unique innovations of the system are as follows: (1) We propose a novel adaptive features extraction algorithm for pulse waveform to improve physiological feature extraction accuracy of sensed pulse waveform data. (2) We propose a light-weight information fusion framework for human symptom identification according to our previous work. (3) We present a robust external pressure control algorithm for pulse measure to obtain stable pulse waveform data on the pulse-sensor nodes. In this demo, we will demonstrate the working procedure of the system and prove the innovations summarized above.