Knowledge-aware recommendation leverages rich item-related factual information in Knowledge Graphs (KGs) to enhance recommendation systems. However, most existing methods focus on developing complex models to extract information from a given KG. They essentially follow a model-centric paradigm, overlooking data quality problems. In practice, KG data exhibits two principal quality problems, namely the noisy knowledge problem and the incomplete knowledge problem, which severely impair the performance of downstream models. To address these problems, we adopt a data-centric paradigm to improve the quality of KG data. Inspired by diffusion models' superior denoising and generation ability by fitting true data distributions, we propose a novel spectral heterogeneous diffusion framework for knowledge-aware recommendation. This framework tailors a diffusion model to capture the recommendation-oriented heterogeneous distribution in the original KG and then converts the fitted distribution into a high-quality KG. Specifically, we design a spectral heterogeneous diffusion model that integrates recommendation prior knowledge to capture task-relevant distribution and aligns its diffusion process with the features of heterogeneous graphs to model heterogeneity. Furthermore, we propose a continuous-discrete mode adapter that transforms the learned continuous distribution into a high-quality discrete KG. The resulting KG is denoised and enriched with task-relevant triples, mitigating noisy and incomplete knowledge problems. Experiments show that our plug-and-play framework can be integrated with any knowledge-aware recommendation model and boost their performance by improving KG quality. The code and theoretical analyses are available at https://github.com/xiangmli/SHGD.

Skeleton sequences for action recognition are with complex temporal dynamics due to various factors such as speed variation and different activities. It is crucial and essential to model variation changes in the temporal dimension. In recent years, skeleton sequence is always modeled as a graph structure, and Graph Convolution Network (GCN) is employed to extract spatial and temporal features of actions. Though GCN has obtained great achievements, they typically employ fixed-size temporal kernels for temporal modeling, which ignore the complex temporal dynamic of actions, especially for long-term as well as short-term modeling. To capture this complex motion pattern effectively, we propose a Dual Multi-Scale Graph Convolutional Network (DMS-GCN), which is mainly composed of a Deformable Temporal Kernel (DTK) block and a dual multi-scale strategy. Specifically, the DTK block is proposed to flexibly capture complex temporal information of the skeleton sequence. And the dual multi-scale strategy is used to simultaneously accommodate long-term and short-term dynamic information at different scales globally as well as locally. The effectiveness of our proposed method is verified through experiments conducted on two widely used datasets, NTU-RGB+D 60 and NTU-RGB+D 120.

Adaptive learning, which requires the in-depth understanding of students' learning processes and rational planning of learning resources, plays a crucial role in intelligent education. However, how to effectively model these two processes and seamlessly integrate them poses significant implementation challenges for adaptive learning. As core learning resources, exercises have the potential to diagnose students' knowledge states during the learning processes and provide personalized learning recommendations to strengthen students' knowledge, thereby serving as a bridge to boost student-oriented adaptive learning. Therefore, we introduce a novel task called Knowledge-aware Exercise Generative Recommendation (KEGR). It aims to dynamically infer students' knowledge states from their past exercise responses and customizably generate new exercises. To achieve KEGR, we propose an adaptive multi-agent cooperation framework, called ExeGen, inspired by the excellent reasoning and generative capabilities of LLM-based AI agents. Specifically, ExeGen coordinates four specialized agents for supervision, knowledge state perception, exercise generation, and quality refinement through an adaptive loop workflow pipeline. More importantly, we devise two enhancement mechanisms in ExeGen: 1) A human-simulated knowledge perception mechanism mimics students' cognitive processes and generates interpretable knowledge state descriptions via demonstration-based In-Context Learning (ICL). In this mechanism, a dual-matching strategy is further designed to retrieve highly relevant demonstrations for reliable ICL reasoning. 2) An exercise generation-adversarial mechanism collaboratively refines exercise generation leveraging a group of quality evaluation expert agents via iterative adversarial feedback. Finally, a comprehensive evaluation protocol is carefully designed to assess ExeGen. Extensive experiments on real-world educational datasets and a practical deployment in college education demonstrate the effectiveness and superiority of ExeGen. The code is available at https://github.com/dsz532/exeGen.

Multi-behavior recommendation systems aim to incorporate auxiliary behaviors (e.g., click, cart, etc.) to enhance the understanding of sparse target behaviors (e.g., purchase), thereby capturing user preferences more accurately. Currently, multi-behavior recommendation research focuses on modeling the associations between different user behaviors, but ignores the large amount of noise in user interaction data. This noise may come from accidental touches, curiosity, or ineffective operations during the purchasing process, and can be further categorized into two types: 1) hard noise is significantly deviates from the user's true preferences, and 2) soft noise is closer to the user's true preferences. The presence of noise can interfere with the model's ability to accurately identify the user's true preferences. To overcome the aforementioned issue, we innovatively propose a Denoising Model with Memory Pruning and Semantic Guidance for Multi-Behavior Recommendation (DeMBR). The model eliminates different types of noise at the data level and the representation level, respectively. Specifically, since hard noise significantly deviates from user preferences, we design a pruning-based denoising module that leverages a memory bank, which identifies and removes hard noise interactions from the data. Since soft noise reflects some user preferences, we design a semantic guidance denoising module that leverages behaviors with strong expressive ability (e.g., purchase) to guide those with weaker ability (e.g., click), effectively suppressing noise while preserving true's preferences. Finally, we designed a cross-learning module that allows noise-identifying signals to be exchanged between the two modules, and ultimately learn representations that accurately reflect user's preferences. Extensive experiments conducted on two public datasets demonstrate that our model substantially surpasses the state-of-the-art recommendation models. Our code is publicly available at: https://github.com/DeMBR2024/DeMBR.git

GCN-based methods have achieved remarkable performance in skeleton-based action recognition. However, existing methods have not explicitly attempted to remove temporal and spatial redundancy that might introduce additional computational costs. Inspired by the fact that humans always tend to glimpse at overall motion and then zoom into the most important spatio-temporal regions, we propose a Spatio Temporal Focused Dynamic Network (STFD-Net) trained with reinforcement learning for skeleton-based action recognition. Specifically, we first propose a global extractor with Skeleton Pooling Module (SPM) to enable the network to focus on overall motion information with a refined skeleton structure. Then, a local extractor, containing pair-wise part partition, tubelet proposal network, and Partition-Grouped Module (PGM), is proposed to extract local motion details as a complement to the overall motion information. Finally, the dynamic classifier utilizes a recurrent neural network to dynamically terminate the process once the network is adequately confident. Extensive experiments have demonstrated that the proposed network achieves SOTA level performance with lower computational cost on the NTU 60 and NTU 120 dataset.

Extract Method is one of the most frequently performed refactoring operations for the decomposition of large and complex methods, which can also be combined with other refactoring operations to remove a variety of design flaws. Several Extract Method refactoring tools have been proposed based on the quantification of extraction criteria. To the best of our knowledge, state-of-the-art related techniques can be broadly divided into two categories: the first line is non-machine-learning-based approaches built on heuristics, and the second line is machine learning-based approaches built on historical data. Most of these approaches characterize the extraction criteria by deriving software metrics from fine-grained code properties. However, in most cases, these metrics can be challenging to concretize, and their selections and thresholds also largely rely on expert knowledge. Thus, in this paper, we propose an approach to automatically recommend Extract Method refactoring opportunities named REMS via mining multi-view representations from code property graph. We fuse various representations together using compact bilinear pooling and further train machine learning classifiers to guide the extraction of suitable lines of code as new method. We evaluate our approach on two publicly available datasets. The results show that our approach outperforms five state-of-the-art refactoring tools including GEMS, JExtract, SEMI, JDeodorant, and Segmentation in effectiveness and usefulness. Our approach demonstrates an increase of 29% in precision, 15% in recall, and 23% in f1-measure. The results also unveil practical suggestions and provide new insights that benefit additional extract-related refactoring techniques.

Skeleton-based action recognition has attracted great interest in computer vision. For this task, a challenging problem concerns the large intraclass variances of skeleton data, which are mainly caused by diverse viewpoints and subjects, and greatly increase the difficulty of modeling actions through a network. To address the above problem, we propose a variance reduction (VaRe) framework for skeleton-based action recognition, which consists of a view-normalization generative adversarial network (VN-GAN), a subject-independent network (SINet) and a classification network. First, the VN-GAN is responsible for reducing view-induced intraclass variances. Specifically, this network, comprising a generator and a discriminator, is aimed at learning a mapping from a diverse-view skeleton distribution to a unified-view skeleton distribution in an unsupervised manner, thereby generating a view-normalized skeleton. Second, taking the view-normalized skeleton as input, the SINet focuses on reducing the influences of the personal habits of subjects on action recognition. To generate SI skeleton data, the SINet automatically adjusts the human pose according to the human kinematic structure under a classification loss constraint. Finally, without the interference of view- and subject-induced variances, the classification network can concentrate more on learning discriminative action features to predict classes. Furthermore, by combining the joint and bone modalities, the proposed framework achieves competitive performance on three benchmarks: NTU RGB+D, NTU-120 RGB+D and Northwestern-UCLA Multiview Action 3D.

Skeleton-based action recognition has attracted great interest due to low cost of skeleton data acquisition and high robustness to external conditions. A challenging problem of skeleton-based action recognition is the large intra-class gap caused by various viewpoints of skeleton data, which makes the action modeling difficult for network. To alleviate this problem, a feasible solution is to utilize label supervised methods to learn a view-normalization model. However, since the skeleton data in real scenes is acquired from diverse viewpoints, it is difficult to obtain the corresponding view-normalized skeleton as label. Therefore, how to learn a view-normalization model without the supervised label is the key to solving view-variance problem. To this end, we propose a view normalization-based action recognition framework, which is composed of view-normalization generative adversarial network (VN-GAN) and classification network. For VN-GAN, the model is designed to learn the mapping from diverse-view distribution to normalized-view distribution. In detail, it is implemented by graph convolution, where the generator predicts the transformation angles for view normalization and discriminator classifies the real input samples from the generated ones. For classification network, view-normalized data is processed to predict the action class. Without the interference of view variances, classification network can extract more discriminative feature of action. Furthermore, by combining the joint and bone modalities, the proposed method reaches the state-of-the-art performance on NTU RGB+D and NTU-120 RGB+D datasets. Especially in NTU-120 RGB+D, the accuracy is improved by 3.2% and 2.3% under cross-subject and cross-set criteria, respectively.