Large language models (LLMs) are seeing growing adoption in multi-agent systems. In these systems, efficient failure attribution is critical for ensuring robustness and interpretability. Current LLM-based attribution methods often face challenges with lengthy logs and lacking expert knowledge. Drawing inspiration from human debugging strategies, we propose an automated failure attribution framework, Scope Delineation Before Localization, which operates in two key stages: (1) identifying the failure scope and (2) pinpointing the failure step. By decoupling failure attribution into the two stages, our approach alleviates the reasoning workload of LLMs, enabling more precise failure attribution. To support scope delineation, we further introduce two strategies: Stepwise Scope Delineation and Expertise-Assisted Scope Delineation. Experiments on the Who&When dataset validate the efficacy of our two-stage framework, demonstrating substantial improvements over prior methods (up to 24.27% on step-level accuracy).

The rapid development of large language models (LLMs) has relied on access to high-quality, large-scale datasets, yet growing concerns around data privacy and security have spurred substantial research into pre-training data detection. While state-of-the-art (SOTA) methods such as RECALL and CON-RECALL leverage auxiliary prefixes to enhance detection performance, their dependence on individual prefixes introduces notable instability across varying prefix conditions. To address this, we first conduct a theoretical analysis to assess the impact of prefixes on existing prefix-based methods. Building on the analysis, we propose a novel prefix selection method to identify optimal prefixes. Specifically, our method derives two key criteria Discriminability and Symmetry. These criteria serve to quantify the effectiveness of prefixes in detecting pre-training data, enabling precise selection of high-performing candidate prefixes. Experiments on the WikiMIA dataset demonstrate that our method consistently improves the performance of RECALL and CON-RECALL, achieving gains of up to 21.1% in AUC scores while significantly enhancing robustness.

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies.

Deep learning approaches for multimodal aspect-level sentiment classification (MALSC) often require extensive data, which is costly and time-consuming to obtain. To mitigate this, current methods typically fine-tune small-scale pretrained models like BERT and BART with few-shot examples. While these models have shown success, Large Vision-Language Models (LVLMs) offer significant advantages due to their greater capacity and ability to understand nuanced language in both zero-shot and few-shot settings. However, there is limited work on fine-tuning LVLMs for MALSC. A major challenge lies in selecting few-shot examples that effectively capture the underlying patterns in data for these LVLMs. To bridge this research gap, we propose an acquisition function designed to select challenging samples for the few-shot learning of LVLMs for MALSC. We compare our approach, Verification and ZERO-shot feedback acquisition (VERO), with diverse acquisition functions for few-shot learning in MALSC. Our experiments show that VERO outperforms prior methods, achieving an F1 score improvement of up to 6.07% on MALSC benchmark datasets.

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%.

The widespread application of graph data in various high-risk scenarios has increased attention to graph anomaly detection (GAD). Faced with real-world graphs that often carry node descriptions in the form of raw text sequences, termed text-attributed graphs (TAGs), existing graph anomaly detection pipelines typically involve shallow embedding techniques to encode such textual information into features, and then rely on complex self-supervised tasks within the graph domain to detect anomalies. However, this text encoding process is separated from the anomaly detection training objective in the graph domain, making it difficult to ensure that the extracted textual features focus on GAD-relevant information, seriously constraining the detection capability. How to seamlessly integrate raw text and graph topology to unleash the vast potential of cross-modal data in TAGs for anomaly detection poses a challenging issue. This paper presents a novel end-to-end paradigm for text-attributed graph anomaly detection, named CMUCL. We simultaneously model data from both text and graph structures, and jointly train text and graph encoders by leveraging cross-modal and uni-modal multi-scale consistency to uncover potential anomaly-related information. Accordingly, we design an anomaly score estimator based on inconsistency mining to derive node-specific anomaly scores. Considering the lack of benchmark datasets tailored for anomaly detection on TAGs, we release 8 datasets to facilitate future research. Extensive evaluations show that CMUCL significantly advances in text-attributed graph anomaly detection, delivering an 11.13% increase in average accuracy (AP) over the suboptimal.

Federated Multi-View Clustering (FedMVC) aims to uncover consistent clustering structures from distributed multi-view data for clustering while preserving data privacy. However, existing FedMVC methods under vertical settings either ignore the ubiquitous incomplete view issue or require uploading data features, which may lead to privacy leakage or induce high communication costs. To mitigate the view incompleteness issue and simultaneously maintain privacy and efffciency, we propose a novel Federated Multiview Graph Clustering with Incomplete Attribute Imputation (FMVC-IAI). This method constructs a consensus graph structure through complementary multi-view data and then utilizes a non-parametric graph neural network (GNN) to impute missing features. Additionally, it utilizes the adjacency graph as the knowledge carrier to share and fuse the multi-view information. To alleviate the high communication cost due to graph sharing, we proposed to share the anchor graph for global adjacency graph construction, which reduces communication cost and also helps to reduce privacy leakage risk. Extensive experiments demonstrate the superiority of our method in FedMVC tasks with incomplete views.

Multi-view clustering (MVC) has emerged as an important unsupervised multi-view learning method that leverages consistent and complementary information to enhance clustering performance. Recently, tensorized MVC, which processes multi-view data as a tensor to capture their cross-view information, has received considerable attention. However, existing tensorized MVC methods generally overlook deep structures within each view and rely on post-processing to derive clustering results, leading to potential information loss and degraded performance. To address these issues, we develop Tensorial Multi-view Clustering with Deep Anchor Graph Projection (TMVC-DAGP), which performs deep projection on the anchor graph, thus improving model scalability. Besides, we utilize a sparsity regularization to eliminate the redundancy and enforce the projected anchor graph to retain a clear clustering structure. Furthermore, TMVC-DAGP leverages weighted Tensor Schatten $p$-norm to exploit the consistent and complementary information. Extensive experiments on multiple datasets demonstrate TMVC-DAGP's effectiveness and superiority.

Most self-supervised graph learning studies typically follow an offline training paradigm, assuming that all data are readily available.This assumption, however, is not always tenable in real-world scenarios as many graph data are generated continuously.Although several continual graph learning models have emerged and achieved empirical success, they almost all rely on external supervision, making it difficult to adapt to applications with a large amount of unlabeled data from the wild.To be honest, research on self-supervised continual graph learning is still surprisingly in its infancy.Therefore, we select several well-known self-supervised graph embedding models as representatives and explore whether they are resistant to catastrophic forgetting in a continual learning setting.Empirical studies find that self-supervised representation models may be potentially better continual learners than supervised counterparts.Driven by this advantage, we propose a self-supervised continual graph representation learning framework based on adaptive spaced replay on node proxies, named Trace.Inspired by the Complementary Learning System theory, Trace employs a dual-system architecture to simulate the functionality and cooperation of the hippocampus and neocortex in the brain.Among them, the fastlearning system efficiently encodes the current input graph to acquire new knowledge and adaptively extracts node proxies from it as important knowledge cached into the memory through progressive clustering.Drawing inspiration from the Ebbinghaus forgetting curve, the slow-learning system implements adaptive spaced replay based on the memory retention rate of each preceding task instead of the widely used consecutive replay scheme for promising flexibility and efficiency.Experiments under task-incremental and class-incremental learning settings on multiple datasets corroborate

The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on designing complex optimization objectives within the graph domain, overlooking the complementary value of the textual modality, whose features are often encoded by shallow embedding techniques, such as bag-of-words or skip-gram, so that semantic context related to anomalies may be missed. To unleash the enormous potential of textual modality, large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities. Nevertheless, their application to TAG anomaly detection remains nascent, and they struggle to encode high-order structural information inherent in graphs due to input length constraints. For high-quality anomaly detection in TAGs, we propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths. CoLL employs multi-LLM collaboration for evidence-augmented generation to capture anomaly-relevant contexts while delivering human-readable rationales for detected anomalies. Moreover, CoLL integrates a GNN equipped with a gating mechanism to adaptively fuse textual features with evidence while preserving high-order topological information. Extensive experiments demonstrate the superiority of CoLL, achieving an average improvement of 13.37% in AP. This study opens a new avenue for incorporating LLMs in advancing GAD.

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What's more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack.

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability.

Accurate traffic prediction is crucial for real-time traffic management and a variety of subsequent applications. In the domain of traffic prediction, while the latest data-driven studies have achieved satisfactory results, they often overlook the significant problem of data sparsity (i.e., only part of the traffic system is observed) in real-world scenarios which can lead to insufficient data and erroneous predictions. Conventional strategies to counteract sparse data in traffic prediction problems typically involve a two-step process: initially imputing missing data, then predicting traffic state. A critical flaw in these existing methods is their assumption that traffic on adjacent roads equally influences unobserved roads, disregarding the impact of traffic management actions. In response to this challenge, we proposeTMA-GNN, an approach that integrates traffic management actions into traditional data-driven models, treating traffic signal control as governing rules. This approach constrains the attention mechanism between roads, enabling real-time updates of road connectivity and effectively capturing diverse vehicle behavior patterns such as emerging from a residential area or entering a parking lot. These enhancements not only address the limitations of ignoring traffic strategies but also challenge the conventional assumption that vehicles always travel strictly downstream from upstream segments, thereby improving traffic state estimations on both observed and unobserved roads. Nonetheless, in certain extreme scenarios (e.g., when a major residential area is connected by a single road), the unobserved road may be unpredictable and lead to inaccurate imputations. To address this,TMA-GNNintroduces a complementary strategy named EERA for evaluating the robustness of imputed values. This method effectively identifies roads with the highest uncertainty and prioritizes them for sensor installation, bridging data gaps on such unobserved roads. We conducted experiments on both synthetic and real-world datasets to validate the efficacy of theTMA-GNNframework and its components. Additionally, we carried out a series of case studies demonstrating the practical utility of EERA in real-world scenarios.

RGB-D salient object detection (SOD) has gained tremendous attention in recent years. In particular, transformer has been employed and shown great potential. However, existing transformer models usually overlook the vital edge information, which is a major issue restricting the further improvement of SOD accuracy. To this end, we propose a novel edge-aware RGB-D SOD transformer, called EM-Trans, which explicitly models the edge information in a dual-band decomposition framework. Specifically, we employ two parallel decoder networks to learn the high-frequency edge and low-frequency body features from the low- and high-level features extracted from a two-steam multimodal backbone network, respectively. Next, we propose a cross-attention complementarity exploration module to enrich the edge/body features by exploiting the multimodal complementarity information. The refined features are then fed into our proposed color-hint guided fusion module for enhancing the depth feature and fusing the multimodal features. Finally, the resulting features are fused using our deeply supervised progressive fusion module, which progressively integrates edge and body features for predicting saliency maps. Our model explicitly considers the edge information for accurate RGB-D SOD, overcoming the limitations of existing methods and effectively improving the performance. Extensive experiments on benchmark datasets demonstrate that EM-Trans is an effective RGB-D SOD framework that outperforms the current state-of-the-art models, both quantitatively and qualitatively. A further extension to RGB-T SOD demonstrates the promising potential of our model in various kinds of multimodal SOD tasks.

Abnormal subgraph (AS) detection plays a significant role in ensuring the security of many high-impact domains. Unlike node anomaly detection, identifying subgraph anomalies is extremely challenging due to the exponentially large subgraph space caused by various combinations of nodes and edges. Moreover, in the absence of supervisory signals, how to quantify the abnormality of subgraphs poses another pressing challenge. Traditional methods typically rely on handcrafted subgraph anomaly measures, making it hard to handle potential unknown anomalies with limited prior knowledge. Recent deep learning-based techniques are predominantly designed to discover individual node anomalies, which could be suboptimal for AS detection due to the inconsideration of collaborative behaviors between nodes in the subgraph. In fact, existing studies have put very little effort into this task, and even dedicated performance evaluation metrics are not yet available. To address the above challenges and promote related research, in this article, we propose a end-to-end unsupervised subgraph anomaly detection framework (EndSubG), which jointly models subgraph partition and AS detection as a whole instead of treating them as two separate stages. Specifically, EndSubG uncovers potential AS boundaries that violate the Homophily assumption by modeling the edge existence probability, then achieves anomaly-aware graph embedding and subgraph partition based on the refined topology. By forming a coarsened subgraph network, EndSubG picks out subgraph anomalies by learning the "subgraph-vicinity" matching patterns. Additionally, we design an evaluation metric weighted normalized mutual information centered on AS (AS-WNMI) specifically for subgraph anomaly detection, which is a variant of vanilla NMI and quantifies detection performance from both subgraph partition and anomaly recognition. The experimental results on synthetic and real-world datasets corroborate the superiority of end-to-end unsupervised subgraph anomaly detection framework (EndSubG) in terms of area under the curve (AUC), average precision (AP), and AS-WNMI. We also provide an intuitive analysis of the detected subgraphs through visualization for better understanding.

Tax evasion, an unlawful practice in which taxpayers deliberately conceal information to avoid paying tax liabilities, poses significant challenges for tax authorities. Effective tax evasion detection is critical for assisting tax authorities in mitigating tax revenue loss. Recently, machine-learning-based methods, particularly those employing positive and unlabeled (PU) learning, have been adopted for tax evasion detection, achieving notable success. However, these methods exhibit two major practical limitations. First, their success heavily relies on the strong assumption that the label frequency (the fraction of identified taxpayers among tax evaders) is known in advance. Second, although some methods attempt to estimate label frequency using approaches like Mixture Proportion Estimation (MPE) without making any assumptions, they subsequently construct a classifier based on the error-prone label frequency obtained from the previous estimation. This two-stage approach may not be optimal, as it neglects error accumulation in classifier training resulting from the estimation bias in the first stage. To address these limitations, we propose a novel PU learning-based tax evasion detection framework called RR-PU, which can revise the bias in a two-stage synergistic manner. Specifically, RR-PU refines the label frequency initialization by leveraging a regrouping technique to fortify the MPE perspective. Subsequently, we integrate a trainable slack variable to fine-tune the initial label frequency, concurrently optimizing this variable and the classifier to eliminate latent bias in the initial stage. Experimental results on three real-world tax datasets demonstrate that RR-PU outperforms state-of-the-art methods in tax evasion detection tasks.

Partial multi-view clustering is a challenging and practical research problem for data analysis in real-world applications, due to the potential data missing issue in different views. However, most existing methods have not fully explored the correlation information among various incomplete views. In addition, these existing clustering methods always ignore discovering discriminative features inside the data itself in this unsupervised task. To tackle these challenges, we propose Partial Multi-View Clustering via Self-Supervised \textbf{N}etwork (PVC-SSN) in this paper. Specifically, we employ contrastive learning to obtain a more discriminative and consistent subspace representation, which is guided by a self-supervised module. Self-supervised learning can exploit effective cluster information through the data itself to guide the learning process of clustering tasks. Thus, it can pull together embedding features from the same cluster and push apart these from different clusters. Extensive experiments on several benchmark datasets show that the proposed PVC-SCN method outperforms several state-of-the-art clustering methods.

Deep Evidential Regression (DER) places a prior on the original Gaussian likelihood and treats learning as an evidence acquisition process to quantify uncertainty. For the validity of the evidence theory, DER requires specialized activation functions to ensure that the prior parameters remain non-negative. However, such constraints will trigger evidence contraction, causing sub-optimal performance. In this paper, we analyse DER theoretically, revealing the intrinsic limitations for sub-optimal performance: the non-negativity constraints on the Normal Inverse-Gamma (NIG) prior parameter trigger the evidence contraction under the specialized activation function, which hinders the optimization of DER performance. On this basis, we design a Non-saturating Uncertainty Regularization term, which effectively ensures that the performance is further optimized in the right direction. Experiments on real-world datasets show that our proposed approach improves the performance of DER while maintaining the ability to quantify uncertainty.

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks.

Representing the spatial properties of facial attributes is a vital challenge for facial attribute recognition (FAR). Recent advances have achieved the reliable performances for FAR, benefiting from the description of spatial properties via extra prior information. However, the extra prior information might not be always available, resulting in the restricted application scenario of the prior-based methods. Meanwhile, the spatial ambiguity of facial attributes caused by inherent spatial diversities of facial parts is ignored. To address these issues, we propose a prior-free method for attribute spatial decomposition (ASD), mitigating the spatial ambiguity of facial attributes. The attribute components could be formally described in terms of the spatial locations without any extra prior information. Experimental results demonstrate the superiority of ASD compared with state-of-the-art prior-based methods on both CelebA and LFWA.

In label-noise learning, accurately identifying the transition matrix is crucial for developing statistically consistent classifiers. This task is complicated by instance-dependent noise, which introduces identifiability challenges in the absence of stringent assumptions. Existing methods use neural networks to estimate the transition matrix by initially extracting confident clean instances. However, this extraction process is hindered by severe inter-class imbalance and a bias toward selecting unambiguous intra-class instances, leading to a distorted understanding of noise patterns. To tackle these challenges, our paper introduces a Class Rebalance and Geometric Regularization-based Framework (CRGR). CRGR employs a smoothed, noise-tolerant reweighting mechanism to equilibrate inter-class representation, thereby mitigating the risk of model overfitting to dominant classes. Additionally, recognizing that instances with similar characteristics often exhibit parallel noise patterns, we propose that the transition matrix should mirror the similarity of the feature space. This insight promotes the inclusion of ambiguous instances in training, serving as a form of geometric regularization. Such a strategy enhances the model's ability to navigate diverse noise patterns and strengthens its generalization capabilities. By addressing both inter-class and intra-class biases, CRGR offers a more balanced and robust classification model. Extensive experiments on both synthetic and real-world datasets demonstrate CRGR's superiority over existing state-of-the-art methods, significantly boosting classification accuracy and showcasing its effectiveness in handling instance-dependent noise.

Multi-view clustering (MVC) methods based on non-negative matrix factorization (NMF) have gained popularity owing to their ability to provide interpretable clustering results. However, these NMF-based MVC methods generally process each view independently and thus ignore the potential relationship between views. Besides, they are limited in the ability to capture nonlinear data structures. To overcome these weaknesses and inspired by deep learning, we propose a multi-view clustering method based on deep non-negative tensor factorization (MVC-DNTF). With deep tensor factorization, our method can well exploit the spatial structure of the original data and is capable of extracting more deep and nonlinear features embedded in different views. To further extract the complementary information of different views, we adopt the weighted tensor Schatten p-norm regularization term. An optimization algorithm is developed to effectively solve the MVC-DNTF objective. Extensive experiments are performed to demonstrate the effectiveness and superiority of our method.

Multi-view clustering has emerged as an important unsupervised method to process unlabelled multi-view data that provides a comprehensive description of an object. Existing multi-view clustering methods focus on centralized settings but ignore the fact that real-world multi-view data may be distributed across different entities. The sensitive information embedded in multi-view data hinders the cooperative training of multi-view clustering, since data of different views cannot be directly shared, leading to a great challenge to cooperatively exploit the consistent and complementary information of different views. To validate the multi-view clustering in distributed scenarios, in this paper, we propose a novel federated multi-view method named Federated Multi-View Fuzzy C-means with Schatten-p Norm Minimization (FMVFCMSP) which is based on fuzzy C-means and tensor Schatten p-norm. Specifically, we utilize the membership degrees to replace conventional hard clustering assignment in K-means, enabling improved uncertainty handling and less information loss. Moreover, we introduce a tensor Schatten p-norm-based regularizer to fully explore the inter-view complementary information and global spatial structure. We also develop a federated optimization algorithm enabling clients to collaboratively learn the clustering results. Extensive experiments on several datasets demonstrate that our proposed method exhibits superior performance in federated multi-view clustering.

Subsampling is an important technique to tackle the computational challenges brought by big data. Many subsampling procedures fall within the framework of importance sampling, which assigns high sampling probabilities to the samples appearing to have big impacts. When the noise level is high, those sampling procedures tend to pick many outliers and thus often do not perform satisfactorily in practice. To tackle this issue, we design a new Markov subsampling strategy based on Huber criterion (HMS) to construct an informative subset from the noisy full data; the constructed subset then serves as refined working data for efficient processing. HMS is built upon a Metropolis-Hasting procedure, where the inclusion probability of each sampling unit is determined using the Huber criterion to prevent over scoring the outliers. Under mild conditions, we show that the estimator based on the subsamples selected by HMS is statistically consistent with a sub-Gaussian deviation bound. The promising performance of HMS is demonstrated by extensive studies on large-scale simulations and real data examples.

In complementary-label learning (CLL), the complementary transition matrix, denoting the probabilities that true labels flip into complementary labels (CLs) which specify classes observations do not belong to, is crucial to building statistically consistent classifiers. Most existing works implicitly assume that the transition probabilities are identical, which is not true in practice and may lead to undesirable bias in solutions. Few recent works have extended the problem to a biased setting but limit their explorations to modeling the transition matrix by exploiting the complementary class posteriors of anchor points (i.e., instances that almost certainly belong to a specific class). However, due to the severe corruption and unevenness of biased CLs, both anchor points and complementary class posteriors are difficult to predict accurately in the absence of true labels. In this article, rather than directly predicting these two error-prone items, we instead propose a divided-T estimator as an alternative to effectively learn transition matrices from only biased CLs. Specifically, we exploit semantic clustering to mitigate the adverse effects arising from CLs. By introducing the learned semantic clusters as an intermediate class, we factorize the original transition matrix into the product of two easy-to-estimate matrices that are not reliant on the two error-prone items. Both theoretical analyses and empirical results justify the effectiveness of the divided- T estimator for estimating transition matrices under a mild assumption. Experimental results on benchmark datasets further demonstrate that the divided- T estimator outperforms state-of-the-art (SOTA) methods by a substantial margin.

Sentiment Analysis (SA) is a fundamental task in natural language processing, which is widely used in public decision-making. Recently, deep learning have demonstrated great potential to deal with this task. However, prior works have mostly treated SA as a deterministic classification problem, and meanwhile, without quantifying the predictive uncertainty. This presents a serious problem in the SA, different annotator, due to the differences in beliefs, values, and experiences, may have different perspectives on how to label the text sentiment. Such situation will lead to inevitable data uncertainty and make the deterministic classification models feel puzzle to make decision. To address this issue, we propose a new SA paradigm with the consideration of uncertainty and conduct an expensive empirical study. Specifically, we treat SA as the regression task and introduce uncertainty quantification to obtain confidence intervals for predictions, which enables the risk assessment ability of the model and can improve the credibility of SA-aids decision-making. Experiments on five datasets show that our proposed new paradigm effectively quantifies uncertainty in SA while remaining competitive performance to point estimation, in addition to being capable of Out-Of-Distribution~(OOD) detection.

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://github.com/yimingxu24/CLDG.

Practical natural language processing (NLP) tasks often exhibit long-tailed distributions accompanied by noisy labels, posing significant challenges to the generalization and robustness of complex models such as Deep Neural Networks (DNNs). Traditional resampling techniques like oversampling or undersampling, while commonly employed, can easily lead to overfitting. A growing trend involves leveraging small amounts of metadata to learn data weights, alongside the demonstrated benefits of self-supervised pre-training, particularly for under-represented data. In this work, we propose a general framework that addresses both the long-tail and noisy label issues. Our model is adaptively tailored to the problem domain using a contrastive learning approach. The re-weighting module, a feed-forward network, learns explicit weighting functions and adjusts weights based on metadata. Additionally, our framework modifies the weights of terms in the loss function through a combination of polynomial expansion of the cross-entropy loss and focal loss. Extensive experiments consistently demonstrate the superior performance of our proposed framework compared to baseline methods. Finally, our comprehensive sensitivity analysis underscores the efficacy of the proposed framework in handling long-tailed problems and mitigating the adverse effects of noisy labels.

Sequence labeling serves as the most commonly used scheme for Chinese named entity recognition(NER). However, traditional sequence labeling methods classify tokens within an entity into different classes according to their positions. As a result, different tokens in the same entity may be learned with representations that are isolated and unrelated in target representation space, which could finally negatively affect the subsequent performance of token classification. In this paper, we point out and define this problem as Entity Representation Segmentation in Label-semantics. And then we present NerCo: Named entity recognition with Contrastive learning, a novel NER framework which can better exploit labeled data and avoid the above problem. Following the pretrain-finetune paradigm, NerCo firstly guides the encoder to learn powerful label-semantics based representations by gathering the encoded token representations of the same Semantic Class while pushing apart that of different. Subsequently, NerCo finetunes the learned encoder for final entity prediction. Extensive experiments on several datasets demonstrate that our framework can consistently improve the baseline and achieve state-of-the-art performance.

Dichotomous image segmentation (DIS) has a wide range of real-world applications and gained increasing research attention in recent years. In this paper, we propose to tackle DIS with informative frequency priors. Our model, called FP-DIS, stems from the fact that prior knowledge in the frequency domain can provide valuable cues to identify fine-grained object boundaries. Specifically, we propose a frequency prior generator to jointly utilize a fixed filter and learnable filters to extract informative frequency priors. Before embedding the frequency priors into the network, we first harmonize the multi-scale side-out features to reduce their heterogeneity. This is achieved by our feature harmonization module, which is based on a gating mechanism to harmonize the grouped features. Finally, we propose a frequency prior embedding module to embed the frequency priors into multi-scale features through an adaptive modulation strategy. Extensive experiments on the benchmark dataset, DIS5K, demonstrate that our FP-DIS outperforms state-of-the-art methods by a large margin in terms of key evaluation metrics.

In recent years, graph neural networks (GNN) have developed rapidly in various fields, but the high computational consumption of its model training often discourages some graph owners who want to train GNN models but lack computing power. Therefore, these data owners often cooperate with external calculators during the model training process, which will raise critical severe privacy concerns. Protecting private information in graph, however, is difficult due to the complex graph structure consisting of node features and edges. To solve this problem, we propose a new privacy-preserving GNN named MDP based on matrix decomposition and differential privacy (DP), which allows external calculators train GNN models without knowing the original data. Specifically, we first introduce the concept of topological secret sharing (TSS), and design a novel matrix decomposition method named eigenvalue selection (ES) according to TSS, which can preserve the message passing ability of adjacency matrix while hiding edge information. We evaluate the feasibility and performance of our model through extensive experiments, which demonstrates that MDP model achieves accuracy comparable to the original model, with practically affordable overhead.

Prompt-tuning models output relation types as verbalised-type tokens instead of predicting the confidence scores for each relation type. However, existing prompt-tuning models cannot perceive named entities of a relation instance because they are normally implemented on raw input that is too weak to encode the contextual features and semantic dependencies of a relation instance. This study proposes a cue prompt adapting (CPA) model for relation extraction (RE) that encodes contextual features and semantic dependencies by implanting task-relevant cues in a sentence. Additionally, a new transformer architecture is proposed to adapt pre-trained language models (PLMs) to perceive named entities in a relation instance. Finally, in the decoding process, a goal-oriented prompt template is designed to take advantage of the potential semantic features of a PLM. The proposed model is evaluated using three public corpora: ACE, ReTACRED, and Semeval. The performance achieves an impressive improvement, outperforming existing state-of-the-art models. Experiments indicate that the proposed model is effective for learning task-specific contextual features and semantic dependencies in a relation instance.

Nested named entities (nested NEs) refer to the situation where one named entity is included or nested within another named entity, which cannot be recognized by the traditional sequence labeling methods. Recently, span-based methods have become the mainstream methods for nested Named Entity Recognition (nested NER). The fundamental concept behind this method is to enumerate nearly all potential spans as entity mentions and subsequently classify them. However, span-based methods independently classify spans without considering the semantic relations among them, which negatively impacts the span representation. To address the issue, we propose a novel deep learning architecture for nested NER that explores interactive and contrastive relations among spans. Specifically, we design a scale transformation mechanism that embeds geometric information into span representations, which enhances the model's ability to encode interactive relations between spans. Additionally, we introduce a supervised contrastive learning loss that pulls apart highly overlapping spans in the embedding space to encode the contrastive relations. Experiments show that our method achieves state-of-the-art or competitive performance on three publicly nested NER datasets, thus validating its effectiveness.

Tax evasion is an illegal activity in which individuals or entities avoid paying their true tax liability. It has always been a crucial issue for both governments and academic researchers to efficiently detect tax evasion. Recent research has proposed the use of machine learning technology to detect tax evasion and has shown good results in some specific areas. Regrettably, there are still two major obstacles to detect tax evasion. First, it is hard to extract powerful features because of the complexity of tax data. Second, due to the complicated process of tax auditing, labeled data are limited. Such obstacles motivate the contributions of this work. In this paper, we propose a novel tax evasion detection framework named FBNE-PU, a multi-stage method to detect tax evasion in real-life scenarios. In this paper, we perform an in-depth analysis of the characteristics of the transaction network and propose a novel network embedding algorithm, the PnCGCN. It significantly improves detection performance by extracting powerful features from basic features and the tax-related transaction network. Moreover, we utilize nnPU to assign pseudo labels for unlabeled data. Finally, a MLP is trained as the decision function. Experiments on three real-world datasets demonstrate that our method significantly outperforms the comparison methods in the tax evasion detection task.

Modal regression, a widely used regression protocol, has been extensively investigated in statistical and machine learning communities due to its robustness to outlier and heavy-tailed noises. Understanding modal regression's theoretical behavior can be fundamental in learning theory. Despite significant progress in characterizing its statistical property, the majority results are based on the assumption that samples are independent and identical distributed (i.i.d.), which is too restrictive for real-world applications. This paper concerns about the statistical property of regularized modal regression (RMR) within an important dependence structure - Markov dependent. Specifically, we establish the upper bound for RMR estimator under moderate conditions and give an explicit learning rate. Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of the underlying Markov chain. This result shed a new light on characterizing the theoretical underpinning for robust regression.

Recognizing the human emotion automatically from visual characteristics plays a vital role in many intelligent applications. Recently, gait-based emotion recognition, especially gait skeletons-based characteristic, has attracted much attention, while many available methods have been proposed gradually. The popular pipeline is to first extract affective features from joint skeletons, and then aggregate the skeleton joint and affective features as the feature vector for classifying the emotion. However, the aggregation procedure of these emerged methods might be rigid, resulting in insufficiently exploiting the complementary relationship between skeleton joint and affective features. Meanwhile, the long range dependencies in both spatial and temporal domains of the gait sequence are scarcely considered. To address these issues, we propose a novel two-stream network with transformer-based complementarity, termed as TNTC. Skeleton joint and affective features are encoded into two individual images as the inputs of two streams, respectively. A new transformer-based complementarity module (TCM) is proposed to bridge the complementarity between two streams hierarchically via capturing long range dependencies. Experimental results demonstrate that TNTC outperforms state-of-the-art methods on the latest dataset in terms of accuracy.

Failure recovery is one of the most essential problems in the Internet of Things (IoT) systems, especially in crucial scenarios, such as traffic control and healthcare. Meanwhile, with the ever-increasing demand of IoT applications and for latency and security considerations, more and more IoT applications are migrated to large clusters that consist of both cloud and edge servers. However, with the scale of edge–cloud collaborative clusters continue to expand, the risk of system errors and failures is also increasing. The conventional snapshot/rollback method is a powerful way for solving this problem and it is widely used in cloud computing scenarios. But when transplanting to edge–cloud collaborative clusters with the nature of distribution and heterogeneity, it will introduce serious network interruption and guest performance impact. Therefore, in this article, to address the above problems, we propose a duration-aware cluster snapshot system, named Phalanx, which can take live snapshots of edge–cloud collaborative clusters with low performance overhead. In Phalanx, we use the low-overhead precopy model and first propose a virtual machine (VM) snapshot duration prediction method that can accurately predict the snapshot duration of each single VM. Then, based on the prediction results, we coordinate the snapshot process to ensure the whole cluster has a consistency-friendly schedule, thereby solving the network interruption problems and finally, minimizing the adverse performance impact to the guest IoT applications. We implement the prototype of Phalanx on QEMU/KVM platform and conduct several experiments. The experimental results show that Phalanx offers negligible network interruption while incurring 10.68%–20.9% less performance impact over existing solutions.

In recent years, marine animal study has gained increasing research attention, which raises significant demands for fine-grained marine animal segmentation (MAS) techniques. In addition, deep learning has been widely adopted for object segmentation and has achieved promising performance. However, deep-based MAS is still lack of investigation due to the shortage of a large-scale MAS dataset. To tackle this issue, we construct the first large-scale MAS dataset, calledMAS3K, which consists of 3,103 images from different types, including camouflaged marine animal images, common marine animal images, and underwater images without marine animals. Furthermore, we consider different underwater conditions, such as low illumination, turbid water quality, photographic distortion, etc. Each image fromMAS3Kdataset has rich annotations, including an object-level mask, a category name, attributes, and a camouflage method (if applicable). Furthermore, we propose a novel MAS network, called Enhanced Cascade Decoder Network (ECD-Net), which consists of multiple Interactive Feature Enhancement Modules (IFEMs) and Cascade Decoder Modules (CDMs). InECD-Net, the IFEMs are first utilized to extract rich multi-scale features. The resulting features are then fed to the CDMs for accurately segmenting marine animals from complex underwater environments. We perform extensive experiments to compareECD-Netwith 10 cutting-edge object segmentation models. The results demonstrate thatECD-Netis an effective MAS model and outperforms the cutting-edge models, both qualitatively and quantitatively.

Live virtual machine migration technique allows migrating an entire OS with running applications from one physical host to another, while keeping all services available without interruption. It provides a flexible and powerful way to balance system load, save power, and tolerate faults in data centers. Meanwhile, with the stringent requirements of latency, scalability, and availability, an increasing number of applications are deployed across distributed data-centers. However, existing live migration approaches still suffer from long downtime and serious performance degradation in cross data-center scenes due to the mass of dirty retransmission, which limits the ability of cross data-center scheduling. In this paper, we propose a system named Memory/disk operation aware Lightweight VM Live Migration across data-centers with low performance impact (MLLM). It significantly improves the cross data-center migration performance by reducing the amount of dirty data in the migration process. In MLLM, we predict disk read workingset (i.e., more frequently read contents) and memory write workingset (i.e., more frequently write contents) based on the access sequence traces. And then we adjust the migration models and data transfer sequence by the workingset information. We further proposed an improved algorithm for workingset estimation. Moreover, we discussed the potential use of machine learning (ML) to enhance the performance of the VM migration and also propose a two-level hierarchical network model to make the ML-based prediction more efficient. We implement MLLM and its improved versions on the QEMU/KVM platform and conduct several experiments. The experimental results show that 1) MLLM averagely reduces 62.9% of total migration time and 36.0% service downtime over existing methods; 2) The improved workingset estimation algorithm reduces 9.32% memory pre-copy time on average over the original algorithm.

The typical RDF querying method is a structured query language such as SPARQL. However, a structured query language requires issuers to understand the data model and query language syntax, limiting the accessibility of RDF data. The keyword query is regarded as an intuitive way for searching the RDF data. This paper proposes a keyword query approach based on the community structure of the RDF entity graph, which utilizes the characteristics of the community structure on the RDF graph. We propose a novel RDF entity graph model by designing an efficient entity index mechanism by treating the RDF entity as the virtual document, which reduces the graph scale while improving the efficiency of retrieving entities. We design an effective hierarchical and overlapping community-based index mechanism on the RDF entity graph, improving the efficiency and accuracy of the subgraph (sub-community) matching. Our approach takes full advantage of the schema of the RDF data and the community structural characteristic of the RDF entity graph. We evaluate our approach using two real-world datasets, and the experiment demonstrates the effectiveness and efficiency of our approach.

Tax evasion is a serious economic problem for many countries, as it can undermine the government's tax system and lead to an unfair business competition environment. Recent research has applied data analytics techniques to analyze and detect tax evasion behaviors of individual taxpayers. However, they have failed to support the analysis and exploration of the related party transaction tax evasion (RPTTE) behaviors (e.g., transfer pricing), where a group of taxpayers is involved. In this paper, we present TaxThemis, an interactive visual analytics system to help tax officers mine and explore suspicious tax evasion groups through analyzing heterogeneous tax-related data. A taxpayer network is constructed and fused with the respective trade network to detect suspicious RPTTE groups. Rich visualizations are designed to facilitate the exploration and investigation of suspicious transactions between related taxpayers with profit and topological data analysis. Specifically, we propose a calendar heatmap with a carefully-designed encoding scheme to intuitively show the evidence of transferring revenue through related party transactions. We demonstrate the usefulness and effectiveness of TaxThemis through two case studies on real-world tax-related data and interviews with domain experts.

Tax evasion refers to the illegal act of taxpayers using deception and concealment to avoid paying taxes. How to detect tax evasion effectively is always an important topic for the government and academic researchers. Recent research has proposed using machine learning technologies to detect tax evasion and has achieved good results in some specific conditions. However, recent methods have three shortcomings. First, recent methods mainly use the basic features extracted based on expert experience. Second, recent methods do not make full use of the edge features of the transaction network. Third, recent methods cannot adapt to a dynamic transaction network. To overcome these challenges, we propose a novel tax evasion detection method, the temporal edge enhanced graph attention network (T-EGAT), which combines the edge enhanced graph attention network (EGAT) and the recurrent weighted average unit (RWA). Specifically, the EGAT is used to learn complex topological structures for capturing spatial dependence and the RWA is used to learn the dynamic changes of transaction data for capturing temporal dependence. Experimental tests using real-world tax data demonstrate that our method achieves better performance at detecting tax evaders than existing methods.

Invoices serve as records of financial transactions of taxpayers and significant basis to controlling tax source and collection of tax, via analyzing which, we can discern diversified tasks of tax risk, such as industry identification, hidden transaction detection, and illegal behavior mining. Among all the existing studies related to the identification of tax risk, there are some weaknesses through the machine learning model and network analysis because of the dependence on tax knowledge. Different from the manual selection of indicators and the manual definitions mode with the guidance of tax knowledge in the past, in this paper, we propose a novel method, namely, network embedding based on upstream and downstream for tax risk identification (NEUD-TRI), which considers the taxpayers serving as both seller and purchaser. The method designs optimization functions respectively to capture local and global static network structures and dynamic network structure. In view of the significant discrepancy of weights in the transaction network, this paper normalizes the weight within the range of the upstream and downstream of the vertex. Negative sampling and edge sampling are adopted to deal with the large-scale trait of the transaction network. Empirical results on tax data-sets of Shanxi province substantiate the effectiveness of our models.

The curse of dimensionality is a fundamental difficulty in anomaly detection for high dimensional data. To deal with this problem, the autoencoder based approach is an elegant solution. However, existing works require a clean training dataset that is not always guaranteed in real scenarios. In this paper, we propose a novel anomaly detection method named RVAE-ABFA (robust variational autoencoder with attention based feature adaptation for high dimensional data anomaly detection), which significantly improves the anomaly detection performance when training data is contaminated. Rather than only utilize reconstruction error, we take the learned low dimensional embeddings generated by variational autoencoder into consideration. In RVAE-ABFA, the learned low dimensional embeddings are helpful to detect anomalies in contaminated data because of the ability of variational inference. We also propose an ABFA (attention based feature adaptation) mechanism to adjust the weights of low dimensional embeddings and reconstruction error. Furthermore, we adopt the adversarial training criterion to perform variational inference by the adversarial network named RAAE-ABFA (robust adversarial autoencoder with attention based feature adaptation for high dimensional data anomaly detection) in which we can generate extra samples when training data is not enough. Experimental results on several benchmark datasets show that the proposed method significantly outperforms state-of-the-art unsupervised anomaly detection methods and is more robust when training data is contaminated.

Tax evasion usually refers to the false declaration of taxpayers to reduce their tax obligations; this type of behavior leads to the loss of taxes and damage to the fair principle of taxation. Tax evasion detection plays a crucial role in reducing tax revenue loss. Currently, efficient auditing methods mainly include traditional data-mining-oriented methods, which cannot be well adapted to the increasingly complicated transaction relationships between taxpayers. Driven by this requirement, recent studies have been conducted by establishing a transaction network and applying the graphical pattern matching algorithm for tax evasion identification. However, such methods rely on expert experience to extract the tax evasion chart pattern, which is time-consuming and labor-intensive. More importantly, taxpayers' basic attributes are not considered and the dual identity of the taxpayer in the transaction network is not well retained. To address this issue, we have proposed a novel tax evasion detection framework via fused transaction network representation (TED-TNR), to detecting tax evasion based on fused transaction network representation, which jointly embeds transaction network topological information and basic taxpayer attributes into low-dimensional vector space, and considers the dual identity of the taxpayer in the transaction network. Finally, we conducted experimental tests on real-world tax data, revealing the superiority of our method, compared with state-of-the-art models.

Tax evasion usually refers to taxpayers making false declarations in order to reduce their tax obligations. One of the most common types of tax evasion is to lower the declared taxable amount. This kind of behavior will lead to the loss of tax revenues and damage the fairness of taxation. One of the main roles of the tax authorities is to conduct tax evasion testing through efficient auditing methods. At present, by using machine learning technology along with large amounts of labeled data, tax evasion detection models have achieved good results in specific areas. However, it is a long and costly process for tax experts to label large amounts of data. Since, the data distribution characteristics vary from region to region, models cannot be used across regions. In this paper, we propose a new method called a transferable tax evasion detection method based on positive and unlabeled learning (TTED-PU), which uses only semi-supervised techniques to detect tax evasion in the source domain. In addition, we use the idea of transfer to adapt to the domain to predict tax evasion behavior on the target domain where labeled tax data are unavailable. We evaluate our method on real-world tax data set. The experimental results show that our model can detect tax evasion in both the source and target domains.

The identification of tax evasion plays an important role in ensuring tax order, promoting the level of tax collection and management, and reducing tax losses. With the advancements in data mining technology, many machine learning techniques have yielded results in identifying tax evasion. However, to realize satisfactory performance, these models require large amounts of human annotated data. In the tax field, unlabeled tax data are abundant, data annotation in a single region is expensive, and the distributions of characteristics differ among regions; these factors pose substantial difficulties in the development of an identification model. Existing tax evasion detection methods are either trained for single-region tasks, in which case they perform poorly on inter-region tax evasion identification due to the discrepancies in feature distributions, or utilize labeled data from both the target-task field and different but related auxiliary fields to reuse and transfer knowledge of the target domain data, in which case they cannot deal with scenarios in which there are no labeled data in target audit tasks. Although current unsupervised transfer learning techniques can train models in labeled regions for unlabeled regions, large intra-class distribution discrepancies cannot be perfectly minimized in tax evasion detection scenarios. To better address the above challenges, this paper proposes a general architecture, namely, the unsupervised conditional adversarial networks (UCAN) for tax evasion detection, which is the first approach to solve audit tasks in unlabeled target domains via inter-region transfer. Our architecture establishes an adversarial neural network adding label information in the distribution adapter, which can granularly adapt the joint probability distribution (JPD) of the data. We introduce a constraint that is based on the conditional maximum mean discrepancy (CMMD) of the extracted features to align the conditional probability distribution (CPD) of the deep representation. Our model is formed by combining the distribution adapter and the label predictor to realize end-to-end learning of unsupervised feature transfer. The experimental results demonstrate the outstanding performance of our model in all migration tasks compared with state-of-the-art approaches.

Accurate industry classification of national economic activities as an important component in the construction of economic structure and as the basis of the formulation of economic policies and management of national economic activities has been gaining increasing attention. However, owing to the rapid growth in the number of industries, it is become increasingly difficult for tax bureaus to classify the registered taxpayers' industries. Conventional industrial classification methods only focus on the text features, which can not be analyzed and judged comprehensively according to the registration information, and can only carry on single-label classification since they neglect the primary and secondary relationships between the main and subsidiary industries, which can not meet application requirements. To better address these challenges, this paper proposes a model known as attention based bidirectional RNN for hierarchical industry classification (ABR-HIC), which is the first approach, to the best of our knowledge, to simultaneously address comprehensive registration information utilization and multi-label classification for the main and subsidiary industries. Our architecture establishes a bidirectional RNN using a word-attention mechanism, which is able to capture and fully utilize the text and non-text registration information for feature representation. By separating the taxpayer's primary and secondary multi-label classification problem corresponding to the main and subsidiary industries, respectively, into two subtasks and through multi-task learning, our model can provide comprehensive primary and secondary multi-industrial labels. Experiments were conducted on real tax data-sets of the Shaanxi Province, China and the results demonstrate the outstanding performance of our architecture in terms of both the classification effect and training time compared with those of state-of-the-art approaches.

Tax evasion detection plays a crucial role in reducing tax revenue loss and many efforts have been made to develop detection models based on machine learning techniques. To train an effective model to detect tax evaders, a large amount of data is required, especially sufficient labeled data. However, the expensive and time-consuming annotation process results in small amount of labeled data being available, which makes the development of detection models difficult. To address this issue, we propose a tax evasion detection method based on positive and unlabeled learning (TEDM-PU), to identify tax evasion by utilizing limited annotated tax evasion taxpayers and a large amount of unlabeled data. The TEDM-PU framework consists of three stages: a preprocessing stage extracting taxpayer features based on random forest, a pseudo labeling stage assigning pseudo labels to unlabeled samples based on PUAdapter, and a model training stage based on LightGBM method. To evaluate the effectiveness of our proposed TEDM-PU, we conduct experimental tests on real-world tax data. The results demonstrate that TEDM-PU method can detect tax evaders with higher accuracy and better interpretability than state-of-the-art methods.

In this demonstration, we present ATTENet, a novel visual analytic system for detecting and explaining suspicious affiliated-transaction-based tax evasion (ATTE) groups. First, the system constructs a taxpayer interest interacted network, which contains economic behaviors and social relationships between taxpayers. Then, the system combines basic features and structure features of each group in the network with network embedding method structure2Vec, and then detects suspicious ATTE groups with random forest algorithm. Last, to explore and explain the detection results, the system provides an ATTENet visualization with three coordinated views and interactive tools. We demonstrate ATTENet on a non-confidential dataset which contains two years of real tax data obtained by our cooperative tax authorities to verify the usefulness of our system.

How do learners schedule their online learning? This issue is concerned by both course instructors and researchers, especially in the context of self-paced online learning environment. Many indicators and methods have been proposed to understand and improve the time management of learning activities, however, there are few tools of visualizing, comparing and exploring the time management to gain intuitive understanding. In this demo, we introduce the LearnExp, an interactive visual analytic system designed to explore the temporal patterns of learning activities and explain the relationships between academic performance and these patterns. This system will help instructors to comparatively explore the distribution of learner activities from multiple aspects, and to visually explain the time management of different learner groups with the prediction of learning performance.

The demo presents TaxVis, a visual detection system for tax auditor. The system supports tax evasion group detection based on a two-phase detection approach. Different from the pattern matching based methods, this two-phase method can analyze the suspicious groups automatically without artificial extraction of tax evasion patterns. In the first phase, we use a network embedding method node2vec to learn representations that embed corporations from a Corporation Associated Network (CANet), and use LightGBM to calculate a suspicious score for each corporation. In the second phase, the system use three detection rules to analyze the transaction anomaly around the suspicious corporations. According to these transaction anomalies, we can discover potential suspicious tax evasion groups. We demonstrate TaxVis on tax data of Shaanxi province in China to verify the usefulness of the system.

Caching contents on edge computing-enabled small cell base stations (ECSBSs) has become a promising technology for mitigating burdens of macro cell base stations and offloading data from mobile users. However, as ECSBSs may be malicious, providing a secure caching scheme becomes a challenge. In this paper, we propose a novel secure caching scheme in heterogeneous networks for multihoming users. First, to provide the cached contents, a trust mechanism is designed to verify the reliability of each ECSBS. Then, in order to guarantee the integrity of cached contents and preserve the privacy of mobile users, a Chinese remainder theorem-based privacy preservation protocol is proposed. Next, we investigate the interactions among mobile users and ECSBSs by Stackelberg game, where the trusted ECSBSs are selected to provide caching resources for mobile users with multihoming access. In addition, we analyze the Stackelberg equilibrium to jointly maximize the utilities of ECSBSs and mobile users. Extensive simulations validate the efficiency of the proposed scheme with the reliability and effectiveness to cache contents.

Massive video resources were produced to meet the needs of learning knowledge and skills anytime and anywhere through internet. Therefore, whether these video resources were fully utilized by students is an important issue for schools and teachers. This paper proposes three indicators based on student's log data and course's video information to measure the utilization of video resources. In addition, the proposed indicators are applied in a case study to analyze how different utilization patterns affect students' academic performance in a large-scale online distance education context.

To save energy during content delivery in green cities, caching contents on edge nodes that are placed near mobile social users has been advocated recently. However, how to allocate the limited caching resources with secure content delivery becomes a new challenge. Therefore, in this paper, we present a novel theoretical model to deliver secure content with edge nodes in order to save energy for green cities. First, we present a reverse auction game to encourage edge nodes to cooperatively provide caching services with incentives. With the model, mobile users can determine the candidate of edge node to cache content based on the interaction between mobile users and edge nodes. Second, a trust management method is designed to evaluate the reliability of the selected candidate of edge node by considering the direct trust evaluation. Finally, extensive simulations show that the proposal can save energy with a secure content delivery where both the delay to obtain the content and the caching ratio can be improved compared with the conventional methods.

Cloud computing is a promising technology having ability to influence the way of the provision of computing and storage resources through virtual machine (VM). VM Consolidation is an efficient way to improve power efficiency and quality guarantee for on-demand services. However, it is an integer programming problem and as well as a NP-hard problem to find optimal solutions within polynomial time. In this paper, the VM consolidation problem is formulated as a multi-objective optimization problem, which has three conflicting objectives, i.e., reducing power consumption, achieving good load balancing and shortening VM migration time. We propose a multi-objective optimization algorithm based on biogeography-based optimization (BBO) for the VM consolidation problem, which is named as MBBO/DE: Multi-objective Biogeography-Based Optimization algorithm hybrid with Differential Evolution. It utilizes cosine migration model, differential strategies and Gaussian mutation model to improve the quality of habitats and the ability of finding optimal solutions. Experiments have been conducted to evaluate the effectiveness of MBBO/DE using synthetic and real-world instances. Experimental results show that MBBO/DE obtains a better performance while simultaneously reducing power consumption and achieving good load balancing within a satisfactory time as compared to genetic algorithm (GA), differential evolution (DE), ant colony optimization (ACO) and BBO.

Zebra fish, as a popular experimental model organism, has been frequently used in biomedical research. For observing, analysing and recording labelled transparent features in zebra fish images, it is often efficient and convenient to adopt the fluorescence microscopy. However, the acquired z-stack images are always blurred, which makes deblurring/deconvolution critical for further image analysis. In this paper, we propose a Bayesian Maximum a-Posteriori (MAP) method with the sparse image priors to solve three-dimensional (3D) deconvolution problem for Wide Field (WF) fluorescence microscopy images from zebra fish embryos. The novel sparse image priors include a global Hyper-Laplacian model and a local smooth region mask. These two kinds of prior are deployed for preserving sharp edges and suppressing ringing artifacts, respectively. Both synthetic and real WF fluorescent zebra fish embryo data are used for evaluation. Experimental results demonstrate the potential applicability of the proposed method for 3D fluorescence microscopy images, compared with state-of-the-art 3D deconvolution algorithms.

Hadoop Distributed File System (HDFS) has been widely adopted to support Internet applications because of its reliable, scalable and low-cost storage capability. Blue Sky, one of the most popular e-Learning resource sharing systems in China, is utilizing HDFS to store massive courseware. However, due to the inefficient access mechanism of HDFS, access latency of reading files from HDFS significantly impacts the performance of processing user requests. This paper introduces a two-level correlation based file prefetching approach, taking the characteristics of HDFS into consideration, to improve performance by reducing access latency. Four placement patterns to store prefetched data are presented, with policies to achieve trade-off between performance and efficiency of HDFS prefetching. Moreover, a dynamic replica selection algorithm is investigated to improve the efficiency of HDFS prefetching. The proposed prefetching approach has been implemented in Blue Sky, and experimental results prove that correlation based file prefetching can significantly reduce access latency therefore improve performance of Hadoop-based Internet applications.

Recently the research community has believed that an e-learning ecosystem is the next generation e-learning. However, the current models of e-learning ecosystems lack the support of underlying infrastructures, which can dynamically allocate the required computation and storage resources for e-learning ecosystems. Cloud computing is a promising infrastructure which provides computation and storage resources as services. Hence, this paper introduces Cloud computing into an e-learning ecosystem as its infrastructure. In this paper, an e-learning ecosystem based on Cloud computing infrastructure is presented. Cloud computing infrastructure and related mechanisms allow for the stability, equilibrium, efficient resource use, and sustainability of an e-learning ecosystem.

With the rapid development of e-learning, stand-alone e-learning information and resource management systems show disadvantages obviously in integration and collaboration. To address the problem, this paper proposes a service-oriented e-learning reference architecture (SOELA), and a federate prototype system SOELS by using SOELA, Web services and portlet. Particularly, the network model and interaction model for collaboration of SOELS are introduced. SOELS verifies the effectiveness of SOELA and meets the integration requirements on e-learning information and resource management systems.