ABSTRACT An attributed network encodes richer information through node and edge attributes. Attributed network representation learning (ANRL) seeks to obtain low‐dimensional node embeddings by jointly modeling structural topology and attribute semantics. Graph neural network (GNN)‐based methods, which leverage recursive message passing, have become the mainstream approach in this area. However, existing reviews provide limited systematic categorization and comparative analysis. In this paper, we classify existing GNN‐based attributed network embedding methods into six categories: graph convolution network (GCN)‐based methods, heterogeneous graph neural network‐based methods, graph autoencoder‐based methods, bidirectional encoder representations from transformers (BERT)‐based methods, hyper‐graph neural network (HGNN)‐based methods, and Bayesian graph neural network‐based methods. We not only summarize a large number of attributed net‐work embedding methods but also analyze and compare these methods. Additionally, we introduce some typical application scenarios in this field. Finally, we discuss the challenges and highlight several future research directions.

Video steganography in the intra prediction mode (IPM) domain embeds secret messages by modifying IPM values. However, such modifications are highly susceptible to detection by video steganalysis techniques, particularly those leveraging recompression-based calibration features. In this paper, the signal restoration phenomenon that occurs during video recompression is first modeled, which reveals the underlying reason for the effectiveness of recompression calibration-based detection features. Based on this insight, a IPM priority-preserving strategy is proposed. This strategy integrates the steganographic modification state with the optimal IPM selection mechanism during recompression, employing dynamic cost revision and joint cost decomposition to guide steganographic modifications toward optimal selection. By aligning modifications with recompression tendency, the proposed method mitigates signal restoration effects, reduces distribution discrepancies in calibration-based detection features, and enhances overall steganographic security. Extensive experimental evaluations demonstrate that the proposed scheme significantly improves resistance against both intra-frame and inter-frame steganalysis features while maintaining superior visual quality and bitrate control.

Most models for Weakly Supervised Video Anomaly Detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly definitions across contexts may introduce inaccuracy in discriminating abnormal and normal events. To show the model what is anomalous, a novel framework is proposed to guide the learning of suspected anomalies from event prompts. Given a textual prompt dictionary of potential anomaly events and the captions generated from anomaly videos, the semantic anomaly similarity between them could be calculated to identify the suspected events for each video snippet. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos, as well as provides a new way to label pseudo anomalies for self-training. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on four datasets, namely XD-Violence, UCF-Crime, TAD, and ShanghaiTech. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC (86.5%, 90.4%, 94.4%, and 97.4%). Furthermore, it shows promising performance in open-set and cross-dataset cases. The data, code, and models can be found at: https://github.com/shiwoaz/lap .

Video anomaly detection plays a significant role in intelligent surveillance systems. To enhance model's anomaly recognition ability, previous works have typically involved RGB, optical flow, and text features. Recently, dynamic vision sensors (DVS) have emerged as a promising technology, which capture visual information as discrete events with a very high dynamic range and temporal resolution. It reduces data redundancy and enhances the capture capacity of moving objects compared to conventional camera. To introduce this rich dynamic information into the surveillance field, we created the first DVS video anomaly detection benchmark, namely UCF-Crime-DVS. To fully utilize this new data modality, a multi-scale spiking fusion network (MSF) is designed based on spiking neural networks (SNNs). This work explores the potential application of dynamic information from event data in video anomaly detection. Our experiments demonstrate the effectiveness of our framework on UCF-Crime-DVS and its superior performance compared to other models, establishing a new baseline for SNN-based weakly supervised video anomaly detection.

Recently, Spiking Neural Networks (SNNs) have demonstrated rich potential in computer vision domain due to their high biological plausibility, event-driven characteristic and energy-saving efficiency. Still, limited annotated event-based datasets and immature SNN architectures result in their performance inferior to that of Artificial Neural Networks (ANNs). To enhance the performance of SNNs on their optimal data format, DVS data, we explore using RGB data and well-performing ANNs to implement knowledge distillation. In this case, solving cross-modality and cross-architecture challenges is necessary. In this paper, we propose cross knowledge distillation (CKD), which not only leverages semantic similarity and sliding replacement to mitigate the cross-modality challenge, but also uses an indirect phased knowledge distillation to mitigate the cross-architecture challenge. We validated our method on main-stream neuromorphic datasets, including N-Caltech101 and CEP-DVS. The experimental results show that our method outperforms current State-of-the-Art methods. The code will be available at https://github.com/ShawnYE618/CKD.

Event cameras detect per-pixel brightness changes and output asynchronous event streams with high temporal resolution, high dynamic range, and low latency. However, the unstructured nature of event streams means that humans cannot analyze and interpret them in the same way as natural images. Event-based video reconstruction is a widely used method aimed at reconstructing intuitive videos from event streams. Most reconstruction methods based on traditional artificial neural networks (ANNs) have high energy consumption, which counteracts the low-power advantage of event cameras. Spiking neural networks (SNNs) are a new generation of event-driven neural networks that encode information via discrete spikes, which leads to greater computational efficiency. Previous methods based on SNNs overlooked the asynchronous nature of event streams, leading to reconstructions that suffer from artifacts, flickering, low contrast, etc. In this work, we analyze event streams and spiking neurons and explain poor reconstruction quality. We specifically propose a novel spatial-temporal heterogeneous (STH) spiking neuron suitable for reconstructing asynchronous event streams. The STH neuron adjusts the membrane decay coefficient adaptively and has better spatiotemporal perception. In addition, we propose a temporal-frequency calibration module (TFCM) based on the Fourier transform to improve the contrast of the reconstructions. On the basis of the above proposed neuron and module, we construct two SNN-based models, referred to as the STHSNN and TFCSNN. The goal of the former is to reduce the artifacts and flickering in reconstructions, whereas the latter focuses on enhancing the contrast. The experimental results demonstrate that our models can yield reconstructions in various scenarios, achieving better quality and lower energy consumption than previous SNNs. Specifically, the TFCSNN and STHSNN achieve top-2 performance among the SNN-based models, with energy consumption reductions of 3.48 times and 12.40 times, respectively.

Hyperspectral change detection is a critical technology in remote sensing, widely applied in urban planning, environmental monitoring, and disaster detection. However, hyperspectral data exhibits higher spectral dimensionality compared to conventional RGB data, making existing methods struggle to balance high accuracy and low energy consumption. As the third generation of neural networks, spiking neural networks (SNNs) demonstrate the advantage of low energy efficiency, but the iterative computation process in spiking neurons significantly increases training and inference burdens when applied to hyperspectral change detection. To address these challenges, we propose a novel spiking Transformer with parallel neurons and memory-enhanced attention for hyperspectral change detection named SpikeHCD, the first SNNs specifically designed for hyperspectral change detection. SpikeHCD not only maintains low-energy advantage but also employs a probability-driven parallel spiking neurons (PPSN) to improve computational efficiency, enabling more effective application in remote sensing tasks. We further design a memory-enhanced spiking attention (MSA) module to enhance temporal modeling capability, and thoroughly extract spatial-spectral features. Additionally, a spiking difference module (SDM) is introduced to capture change features across different timesteps. Experimental results demonstrate that SpikeHCD can achieve several state-of-the-art (SOTA) results on multiple hyperspectral datasets, with faster detection, lower energy consumption, and fewer number of parameters. The codes are available at https://github.com/mzhcode/HCD_snn.

How to properly align the extracted visual features with certain semantic embeddings of unseen objects is crucial to the problem of Zero-Shot Object Detection (ZSD). To give a better guess of those unseen visual features, a partitioned contrast strategy is proposed in this paper to train the visual and attribute feature alignment networks. To be specific, four types of contrast are considered, including the visual-to-visual, visual-to-attribute, attribute-to-visual and attribute-to-attribute contrasts. Combining with two cross-batch memory banks of the visual features and unseen attribute features, it is effective to adjust the alignment rules for unseen visual features. Experimental results on the MS-COCO dataset show the superiority of the proposed model. Our code is available at: https://github.com/lihh1023/PCFA-ZSD.

Abstract Coloring an animation sketch sequence is a challenging task in computer vision since the information contained in line sketches is too sparse, and the colors need to be uniform between continuous frames. Many the existing colorization algorithms can only be applied to one image and can be considered color filling algorithms. Such algorithms only provide a color result that fits within a reasonable range and can not be applied to the coloring of frame sequences. This paper proposes an end‐to‐end two‐stage optical flow colorization network to solve the animation frame sequence colorization problem. The first stage of the network finds the direction of the color pixel flow from the detail change between a given reference frame and the next frame of line artwork and then completes the initial coloring process. The second stage of the network performs color correction and clarifies the output of the first stage. Since our algorithm does not directly colorize the image but finds the path of the color change to colorize it, it ensures a consistent color space for the sequence frames after colorization. We conduct experiments on an animation dataset, and the results show that our algorithm is effective. The code is available at https://github.com/silenye/Colorization .

Cross-modal recipe retrieval is vital for transforming visual food cues into actionable cooking guidance, making culinary creativity more accessible. Existing methods separately encode the recipe Title, Ingredient, and Instruction using different text encoders, then aggregate them to obtain recipe feature, and finally match it with encoded image feature in a joint embedding space. These methods perform well but require significant computational cost. In addition, they only consider matching the entire recipe and the image but ignore the fine-grained correspondence between recipe components and the image, resulting in insufficient cross-modal interaction. To this end, we propose U nified T ext E ncoder with F ine-grained C ontrastive L earning (UTE-FCL) to achieve a simple but efficient model. Specifically, in each recipe, UTE-FCL first concatenates each of the Ingredient and Instruction texts composed of multiple sentences as a single text. Then, it connects these two concatenated texts with the original single-phrase Title to obtain the concatenated recipe. Finally, it encodes these three concatenated texts and the original Title by a Transformer-based Unified Text Encoder (UTE). This proposed structure greatly reduces the memory usage and improves the feature encoding efficiency. Further, we propose fine-grained contrastive learning objectives to capture the correspondence between recipe components and the image at Title, Ingredient, and Instruction levels by measuring the mutual information. Extensive experiments demonstrate the effectiveness of UTE-FCL compared to existing methods.

Abstract In the field of object detection, there is often a high level of occlusion in real scenes, which can very easily interfere with the accuracy of the detector. Currently, most detectors use a convolutional neural network (CNN) as a backbone network, but the robustness of CNNs for detection under cover is poor, and the absence of object pixels makes conventional convolution ineffective in extracting features, leading to a decrease in detection accuracy. To address these two problems, we propose VFN (A Vision Enhancement and Feature Fusion Multiscale Detection Network), which first builds a multiscale backbone network using different stages of the Swin Transformer, and then utilizes a vision enhancement module using dilated convolution to enhance the vision of feature points at different scales and address the problem of missing pixels. Finally, the feature guidance module enables features at each scale to be enhanced by fusing with each other. The total accuracy demonstrated by VFN on both the PASCAL VOC dataset and the CrowdHuman dataset is better than that of other methods, and its ability to find occluded objects is also better, demonstrating the effectiveness of our method.The code is available at https://github.com/qcw666/vfn .

Abstract With the rapid growth of information in the Internet era, people are in great need of recommendation methods to filter information. At present, recommendation methods which based on heterogeneous information network (HIN) have attracted wide attention. Recently, HIN-based recommendation methods need to be modeled from two aspects: node structural association and semantic association. To this end, we propose a graph contrastive learning model based on structural and semantic view for HIN recommendation (GCL-SS). GCL-SS utilizes U-I interactive view to obtain node structural embeddings, and utilizes U-I semantic view to obtain node semantic embeddings. Based on these two kinds of embeddings, we establish a self-supervised contrastive learning mechanism to effectively integrate structural information and semantic information of user (item) nodes in HIN, and finally learn a more discriminative user (item) embedding. In addition, in order to strengthen the semantic association between nodes, we innovatively utilize time sequence encoder (TSE), such as LSTM, to encode semantic homogeneous network decomposed by HIN in U-I semantic view. At last, based on the user and item embeddings, we adopt bilinear decoder to model the potential association between user and item, so as to realize rating prediction of user to item. The experimental results on three real datasets confirm that our GCL-SS model performs better than state-of-the-art recommendation methods in rating prediction task. In addition, the results of four ablation experiments indicate that our GCL-SS model can effectively improve the performance of rating prediction in recommendation.

Recently, significant object detection achievements have been emerged for optical remote sensing images. However, the performance and efficiency of small object detection are still highly unsatisfactory because of the scale diversity between the objects; furthermore, small objects always have small amounts of effective information that are difficult to locate. To address this problem, we propose a novel dynamic sensing and correlation loss detector (DCDet) for performing object detection in remote sensing images. The detector consists of two modules: a small-object dynamic sensing (SODS) module and a simple but effective correlation loss function (CrLoss). SODS is utilized to capture the information of small objects in a scale sequence. We consider the feature pyramid as a set of video frames when the camera is zoomed in on the image and use the object focusing module in dynamic sensing to always focus on the small objects in each video frame. The detection performance achieved for small objects is improved by shifting the detector’s attention from the entire image to small objects within the frame to provide a multiscale feature representation of the small objects and their contextual information. The CrLoss is a special correlation loss for remote sensing image object detection tasks and directly optimizes the correlation coefficient to improve the performance of a detector. Extensive experiments conducted on the publicly available DOTA, DIOR-R and HRSC2016 datasets show that our DCDet outperforms the existing state-of-the-art remote sensing object detection methods in terms of many evaluation metrics.

Fairness in clustering has recently received significant attention. The goal of fair clustering is to ensure that a clustering algorithm mitigates or even eliminates bias in the original dataset. Many existing fair clustering algorithms will sometimes generate numerous small clusters to satisfy the fairness constraint. In this article, we present a balanced fair K-means clustering algorithm that integrates a fairness constraint and a balance constraint into the K-means objective function. The proposed model is a tradeoff between the K-means objective and the fairness constraint and their relative importance can be controlled. The balance constraint prevents the generation of small clusters. Experimental results on both real-world and synthetic datasets demonstrate that the proposed method achieves a better fairness performance than some other fair clustering methods, with an acceptable loss of clustering quality in some cases and an improvement in others.

Knowledge distillation aims to achieve model compression by transferring knowledge from complex teacher models to lightweight student models. To reduce reliance on pre-trained teacher models, self-distillation methods utilize knowledge from the model itself as additional supervision. However, their performance is limited by the same or similar network architecture between the teacher and student. In order to increase architecture variety, we propose a new self-distillation framework called restructured self-distillation (RSD), which involves restructuring both the teacher and student networks. The self-distilled model is expanded into a multi-branch topology to create a more powerful teacher. During training, diverse student sub-networks are generated by randomly discarding the teacher's branches. Additionally, the teacher and student models are linked by a randomly inserted feature mixture block, introducing additional knowledge distillation in the mixed feature space. To avoid extra inference costs, the branches of the teacher model are then converted back to its original structure equivalently. Comprehensive experiments have demonstrated the effectiveness of our proposed framework for most architectures on CIFAR-10/100 and ImageNet datasets. Code is available at https://github.com/YujieZheng99/RSD.

Unsupervised video anomaly detection (UVAD) has gained significant attention due to its label-free nature. Typically, UVAD methods can be categorized into two branches, i.e. the one-class classification (OCC) methods and fully UVAD ones. However, the former may suffer from data imbalance and high false alarm rates, while the latter relies heavily on feature representation and pseudo-labels. In this paper, a novel feature reconstruction and disruption model (FRD-UVAD) is proposed for effective feature refinement and better pseudo-label generation in fully UVAD, based on cascade cross-attention transformers, a latent anomaly memory bank and an auxiliary scorer. The clip features are reconstructed using the space-time intra-clip information, as well as cross-inter-clip knowledge. Moreover, instead of blindly reconstructing all training features as OCC methods, a new disruption process is proposed to cooperate with the feature reconstruction simultaneously. Using the collected pseudo anomaly samples, it is able to emphasize the feature differences between normal and abnormal events. Additionally, a pre-trained UVAD scorer is utilized as a different criteria for anomaly prediction, which further refines the pseudo-labels. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on three video benchmarks, namely CUHK Avenue, ShanghaiTech and UCF-Crime. Our proposed model (FRD-UVAD) achieves the best AUC performance (91.23%, 80.14%, and 82.12%) on all three datasets, surpassing other state-of-the-art OCC and fully UVAD methods. Furthermore, it obtains the lowest false alarm rate with a lower scene dependency, compared with other OCC methods. The code is available athttps://github.com/tcc-power/FRD-unsupervised-video-anomaly-detection.

Modification of the optimal recursive block encoding process is commonly adopted in HEVC steganography based on block partitioning structure to embed secret messages, which inevitably disrupts the optimal rate distortion optimization process, resulting in a degradation of visual quality and an increase in bit rate. In this paper, we analyze the intra frame recursive block encoding process, categorizing modifications based on block partitioning structures into skip-level and non-skip-level modifications. Then, the rate distortion difference between these two types is compared. Additionally, the Maintenance Principle of Quad-tree Structure is introduced, which aims to preserve the stego quad-tree structure as closely as possible to the original one. Furthermore, a new cover mapping method is designed to expand the embedding capacity, and a quad-tree structure-preserving adaptive steganography is proposed. Extensive experimental results demonstrate that the proposed scheme can embed messages with fewer disruptions to the optimal rate distortion optimization process, ultimately improving the visual quality and reducing the bit rate growth.

Re-identification (Re-ID) technology is important for wildlife conservation and intelligent farm management. With the development of deep learning, the performance of animal ReID based on computer vision has been improved. However, variations in animal pose push a negative impact on recognition performance. In this paper, a Multi-pose Feature Fusion Network (MPFNet) is proposed to improve the performance of the Re-ID. First, we construct three pose modules for the three postures, that is, standing, sitting, and lying, respectively. In each pose module, there are two parallel branches, one is a global branch for extracting global features, and the other is a local branch for extracting local features. In addition, to obtain more effective feature representations, we weighted fusion for the global branching of the three pose modules. We validate the efficiency of MPFNet on both the self-built MPDD dog dataset and the public ATRW Amur Tiger dataset. Experimental results show that MPFNet can obtain better recognition performance than other state-of-the-art Re-ID methods. The source of code will be public available at https://github.com/hezhimin7028/MPFNet.

Knowledge distillation is a common method of model compression, which uses large models (teacher networks) to guide the training of small models (student networks). However, the student may find a hard time absorbing the knowledge from a sophisticated teacher due to the capacity and confidence gaps between them. To address this issue, a new knowledge distillation and refinement (KDrefine) framework is proposed to enlighten the student by expending and refining its network structure. In addition, a confidence refinement strategy is utilized to generate adaptive soften logits for efficient distillation. The experiments show that the proposed framework outperforms state-of-the-art methods on both CIFAR-100 and Tiny-ImageNet datasets. The code is available at https://github.com/YujieZheng99/KDrefine.

Learning hash functions have been widely applied for large-scale image retrieval. Existing methods usually use CNNs to process an entire image at once, which is efficient for single-label images but not for multi-label images. First, these methods cannot fully exploit independent features of different objects in one image, resulting in some small object features with important information being ignored. Second, the methods cannot capture different semantic information from dependency relations among objects. Third, the existing methods ignore the impacts of imbalance between hard and easy training pairs, resulting in suboptimal hash codes. To address these issues, we propose a novel deep hashing method, termed multi-label hashing for dependency relations among multiple objectives (DRMH). We first utilize an object detection network to extract object feature representations to avoid ignoring small object features and then fuse object visual features with position features and further capture dependency relations among objects using a self-attention mechanism. In addition, we design a weighted pairwise hash loss to solve the imbalance problem between hard and easy training pairs. Extensive experiments are conducted on multi-label datasets and zero-shot datasets, and the proposed DRMH outperforms many state-of-the-art hashing methods with respect to different evaluation metrics.

Point of Interest (POI) recommendation system rec-ommends places in which users have never been to but may be in-terested. Traditionally, it centrally collects contextual information and interaction data to model users' preferences, which raises many privacy concerns. The current studies habitually sacrifice the recommendation performance to cope with privacy con-cerns. To protect users' privacy while ensuring the performance of the POI recommendation system, we propose a Ranking-based Federated POI Recommendation with Geographic Effect (RFPG). The RFPG allows users to reserve their private data on local devices to secure privacy. It adaptively constructs an active region to model the geographic effect, enhancing users' personalized preference modeling. In addition, we design a probability-based negative sampling method to protect privacy further and improve recommendation performance. This method calculates the probability of a POI being a negative sample through POI geographic distribution, then combines the positive samples to construct a local triplet training dataset. Theoretical analysis and experiments on two real datasets demonstrate that our proposed RFPG improves the performance of the POI recommendation while protecting users' private data.

Recommender systems are collecting user data to provide better personalized services. However, centralized collection and analysis of users' private data will raise privacy concerns and legal risks. The emergence of federated learning enables training a machine learning model from highly decentralized data. This paper extends the Neural Collaborative Filtering (NCF) method using a federated setting and proposes a privacy-preserving federated recommender system named FedNCF, which can train NCF models without needing to know user's private data. We apply differential privacy to the computed gradients to prevent inference attacks. To improve the utility of differential privacy, we propose an adaptive differential privacy approach that meticulously adjusts the noise scale in each iteration controlled by a decay rate. Our proposed approach provides an explicit mathematical expression to estimate the user's privacy loss by truncated Concentrated Differential Privacy (tCDP). Extensive experiments and analysis demonstrate that FedNCF can achieve competitive performance with the centralized NCF meanwhile effectively protect users' privacy.

Summary Uncertain data is widely used in many practical applications, such as data cleaning, location‐based services, privacy protection, and so on. With the development of technology, data has a tendency to high‐dimensionality. The most common indexes for nearest neighbor search on uncertain data are the R‐Tree and the KD‐Tree. These indexes will inevitably bring about “curse of dimension.” Focus on this problem, article proposes a new hash algorithm, called the LSR‐forest, which based on locality sensitive hashing and R‐Tree, to solve the high‐dimensional uncertain data approximate neighbor search problem. The LSR‐forest can hash similar high‐dimensional uncertain data into a same bucket with a high probability, and then constructs multiple R‐Tree‐based indexes for hashed buckets. When querying, it is possible to judge neighbors by checking the data in the hypercube which the query point is in. One can also adjust the query range automatically by different parameter of k. Many experiments on different datasets are presented in this article. The results show that LSR‐forest has better effectiveness and efficiency than R‐Tree on high‐dimensional datasets.

The cross-domain sequential recommendation aims to predict the next item based on a sequence of recorded user behaviours in multiple domains. We propose a novel Cross-domain Sequential Recommendation approach with Graph-Collaborative Filtering (CsrGCF) to alleviate the sparsity issue of user-interaction data. Specifically, we design time-aware and relation-aware graph attention mechanisms with collaborative filtering to exploit high-order behaviour patterns of users for promising results in both domains. Time-aware Graph Attention mechanism (TGAT) is designed to learn the inter-domain sequence-level representation of items. Relationship-aware Graph Attention mechanism (RGAT) is proposed to learn collaborative items' and users' feature representations. Moreover, to simultaneously improve the recommendation performance in the two domains, a Cross-domain Feature Bidirectional Transfer module (CFBT) is proposed, transferring user's common sharing features in both domains and retaining user's domain-specific features in a specific domain. Finally, cross-domain and sequential information jointly recommend the next items that users like. We conduct extensive experiments on two real-world datasets that show that CsrGCF outperforms several state-of-the-art baselines in terms of Recall and MRR. These demonstrate the necessity of exploiting high-order behaviour patterns of users for a cross-domain sequential recommendation. Meanwhile, retaining domain-specific features is an important step in the process of cross-domain feature bidirectional transferring.

In recent years, the number of traffic accident deaths due to distracted driving has been increasing dramatically. Fortunately, distracted driving can be detected by the rapidly developing deep learning technology. Nevertheless, considering that real-time detection is necessary, three contradictory requirements for an optimized network must be addressed: a small number of parameters, high accuracy, and high speed. We propose a new D-HCNN model based on a decreasing filter size with only 0.76M parameters, a much smaller number of parameters than that used by models in many other studies. D-HCNN uses HOG feature images, L2 weight regularization, dropout and batch normalization to improve the performance. We discuss the advantages and principles of D-HCNN in detail and conduct experimental evaluations on two public datasets, AUC Distracted Driver (AUCD2) and State Farm Distracted Driver Detection (SFD3). The accuracy on AUCD2 and SFD3 is 95.59% and 99.87%, respectively, higher than the accuracy achieved by many other state-of-the-art methods.

As the number of online job postings and users grows dramatically, the accuracy and explainability of personjob fit systems are of increasing concern. An explainable personjob fit system can show reasons when making recommendations to both Human Resources and Job Seekers, building trust between uses and recommendation system while providing accurate recommendation results. However, the existing research on content-based person-job fit mainly focuses on 1) dealing with unstructured statements without effectively using structured information in resumes and jobs, and 2) the explanations of the model stay at the level of giving a few sentences, which leads to a lack of explanations. In this paper, we propose an explainable person-job fit model based on the attention mechanism. We model the resume text through a hierarchical attention mechanism and capture the semantic connections between the resume, structured job text, and unstructured job text through a collaborative attention mechanism to better model the job content and provide both structured and unstructured levels of recommendation explanation. Experiments on a large real dataset show that our model outperforms existing baseline models and provides job recommendation reasons at both levels.

Abstract Researchers usually face difficulties in finding scientific papers relevant to their research interests due to increasing growth. Recommender systems emerge as a leading solution to filter valuable items intelligently. Recently, deep learning algorithms, such as convolutional neural network, improved traditional recommendation technologies, for example, the graph‐based or content‐based methods. However, existing graph‐based methods ignore high‐order association between users and items on graphs, and content‐based methods ignore global features of texts for explicit user preferences. Therefore, this paper proposes a Content‐based and knowledge Graph‐based Paper Recommendation method (CGPRec), which uses a two‐layer self‐attention block to obtain global features of texts for more complete explicit user preferences, and proposes an improved graph convolutional network for modeling high‐order associations on the knowledge graph to mine implicit user preferences. And the knowledge graph in this paper is constructed with concept nodes, user nodes, paper nodes, and other meta‐data nodes. Experimental results on a public dataset, CiteULike‐a, and a real application log dataset, AHData, show that our model outperforms compared with baseline methods.

A growing number of KV storage systems have adopted the Log-Structured-Merge-tree (LSM-tree) due to its excellent write performance. However, the high write amplification in the LSM-tree has always been a difficult problem to solve. The reason is that the design of traditional LSM-tree under-utilizes the data distribution of query, and the design space does not take into account the read and write performance concurrently. As a result, we may sacrifice one to improve another performance. When advancing the writing performance of the LSM-tree, we can only conservatively select the design pattern in the design space to reduce the impact on reading throughputs, resulting in limited improvement. Aiming at the shortcomings of existing methods, a new LSM-tree structure (Leveling-Tiering-Grouped-LSM-tree, LTG-LSM) is proposed by us that combined with reading hotness. The LTG-LSM structure maintains hotness prediction models at each level of the LSM-tree. The structure of the newly generated disk components is determined by the predicted hotness. Finally, a specific compaction algorithm is carried out to handle the compaction between the different structural components and processing workflow hotness changes. Experiments show that the scheme proposed by this paper significantly reduces the write amplification (up to about 71%) of the original LSM-tree with almost no sacrificing reading performance and improves the write throughputs (up to about 24%) in workflows with different configurations.

Since underwater acoustic channels are shared by multiple heterogeneous entities and can suffer from severe interference, underwater acoustic communication networks (UACNs) are faced with the challenge of mitigating interference and improving communication quality by implementing distributed resource allocation approaches. In this article, we introduce the concept of reinforced learning in intelligent control to the UACNs by treating the nodes as intelligent agents and the node networks as multiagent networks. By partitioning the state space and the action space, we formulate a reward function and a search strategy and propose a distributed resource allocation algorithm based on cooperative Q -Learning. In addition, we verify the convergence of the proposed algorithm. Finally, simulation results in two different underwater application scenarios show that the proposed algorithm outperforms the existing algorithms in improving the network transmission capacity, and can reduce the overhead of resource allocation by using cooperative Q -Learning.

In many applications, such as homeland security, image processing, social network, and bioinformatics, it is often required to support an approximate membership query (AMQ) to answer a question like “is an (query) object q near to at least one of the objects in the given data set Ω?” However, existing techniques for processing AMQs require a key parameter, i.e., the distance value, to be defined in advance for the query processing. In this paper, we propose a novel filter, called multi-granularity locality-sensitive Bloom filter (MLBF), which can process AMQs with multiple distance granularities. Specifically, the MLBF is composed of two Bloom filters (BF), one is called basic multi-granularity locality-sensitive BF (BMLBF), and the other is called multi-granularity verification BF (MVBF). The BMLBF is used to store the data objects. It adopts an alignable locality-sensitive hashing (LSH) function family to support multiple granularities. The MVBF is used to reduce the false positive rate of the MLBF. The false negative rate of the MLBF is reduced by applying AND-constructions followed by an OR-construction. In addition, based on the MLBF structure, we suggest a more spaceeffective variant, called the MLBF , to further reduce space cost. Theoretical analyses for estimating false positive/negative rates of the MLBF/MLBF are given. Experiments using synthetic and real data show that the theoretical estimates are quite accurate, and the MLBF/MLBF technique can handle AMQs with low false positive and negative rates for multiple distance granularities.

Bloom filters are widely-used powerful tools for processing set membership queries. However, they are not entirely suitable for many new applications, such as deleting one attribute value according to another attribute value for a set of data objects/items with two correlated attributes. In this paper, we introduce a concept for such an operation, called the associative deletion. To realize this operation, we propose a new Bloom filter data structure, named IABF (Improved Associative deletion Bloom Filter), which keeps the association information on the two correlated attributes of items in the given data set. Based on IABF, we present an algorithm to perform associative deletions, which can be applied to both normal data and streaming data. To further accelerate the operation, we also illustrate a hardware coprocessor implementation for a crucial component of the algorithm. Detailed theoretical analysis and experimental results demonstrate that the presented IABF technique can accurately process associative deletions with controlled false positive and negative rates.