Knowledge editing aims to update specific knowledge in Large Language Models (LLMs) without retraining the entire model. However, existing methods generally struggle to manage the ripple effects of knowledge updates, particularly in multi-hop reasoning tasks, where conflicts between old and new information often lead to shifts in reasoning chains and degraded consistency. To address this issue, a ripple-aware knowledge editing framework, namely EchoEdit, is proposed. EchoEdit introduces the RippleGraph to explicitly model potentially affected knowledge regions and employs a RippleRule generator to dynamically produce diffusion rules, precisely constraining knowledge propagation. Furthermore, we distill a Chain-of-Thought (CoT) planner from an external teacher model, which decouples complex reasoning chain planning into RippleGraph-guided reasoning, thereby alleviating the reasoning burden on low-resource LLMs in multi-hop tasks. Experimental results on the MQuAKE and RIPPLEEDITS multi-hop reasoning benchmarks demonstrate that EchoEdit significantly outperforms existing mainstream methods, effectively enhancing post-edit reasoning consistency and generalization capabilities.

Multi-modal entity alignment aims to identify equivalent entities across different multi-modal knowledge graphs (MMKGs). While prior work has achieved notable progress through improved multi-modal encoding and cross-modal fusion techniques, two critical challenges remain unresolved. First, due to the heterogeneous and often inconsistent sources from which MMKGs are constructed, the quality and informativeness of modalities vary significantly across entities, leading to the modality weighting problem. Second, existing cross-modal fusion mechanisms predominantly emphasize modality-shared information, often at the expense of modality-specific signals that are also essential for precise alignment. To address these issues, we propose HUMEA, a novel framework that integrates hierarchical Mixture-of-Experts (MoE) with unimodal distillation. HUMEA consists of: (1) A hierarchical MoE module comprising intra-modal and inter-modal experts, which adaptively modulates modality contributions by capturing entity representations at fine-to-coarse semantic granularities. In addition, we introduce a contrastive mutual information loss to enhance expert diversity and reduce redundancy. (2) A unimodal distillation strategy that preserves modality-specific information in the fused representations through single-modality alignment and distillation, achieving a balanced integration of shared and unique modality features. Extensive experiments on two benchmark datasets, FB15K-DB15K and FB15K-YAGO15K, demonstrate state-of-the-art performance, validating the effectiveness of our approach.

Large Language Models (LLMs) have shown immense potential in Knowledge Graph Completion (KGC), yet bridging the modality gap between continuous graph embeddings and discrete LLM tokens remains a critical challenge.While recent quantization-based approaches attempt to align these modalities, they typically treat quantization as flat numerical compression, resulting in semantically entangled codes that fail to mirror the hierarchical nature of human reasoning.In this paper, we propose GS-Quant, a novel framework that generates semantically coherent and structurally stratified discrete codes for KG entities.Unlike prior methods, GS-Quant is grounded in the insight that entity representations should follow a linguistic coarse-to-fine logic.We introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook, ensuring that earlier codes capture global semantic categories while later codes refine specific attributes.Furthermore, a Generative Structural Reconstruction module imposes causal dependencies on the code sequence, transforming independent discrete units into structured semantic descriptors.By expanding the LLM vocabulary with these learned codes, we enable the model to reason over graph structures isomorphically to natural language generation.Experimental results demonstrate that GS-Quant significantly outperforms existing text-based and embedding-based baselines.Our code is publicly available at https: //github.com/mikumifa/GS-Quant.

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Graph anomaly detection (GAD), which aims to identify abnormal nodes that deviate from the majority, has become increasingly important in high-stakes Web domains. However, existing GAD methods follow a ''one model per dataset'' paradigm, leading to high computational costs, substantial data demands, and poor generalization when transferred to new datasets. This calls for a foundation model that enables a ''one-for-all'' GAD solution capable of detecting anomalies across diverse graphs without retraining. Yet, achieving this is challenging due to the large structural and feature heterogeneity across domains. In this paper, we propose TFM4GAD, a simple yet effective framework that adapts tabular foundation models (TFMs) for graph anomaly detection. Our key insight is that the core challenges of foundation GAD, handling heterogeneous features, generalizing across domains, and operating with scarce labels, are the exact problems that modern TFMs are designed to solve via synthetic pre-training and powerful in-context learning. The primary challenge thus becomes structural: TFMs are agnostic to graph topology. TFM4GAD bridges this gap by ''flattening'' the graph, constructing an augmented feature table that enriches raw node features with Laplacian embeddings, local and global structural characteristics, and anomaly-sensitive neighborhood aggregations. This augmented table is processed by a TFM in a fully in-context regime. Extensive experiments on multiple datasets with various TFM backbones reveal that TFM4GAD surprisingly achieves significant performance gains over specialized GAD models trained from scratch. Our work offers a new perspective and a practical paradigm for leveraging TFMs as powerful, generalist graph anomaly detectors.

Graph anomaly detection (GAD) aims to identify nodes that deviate from normal patterns in structure or features. While recent GNN-based approaches have advanced this task, they struggle with two major challenges: 1) homophily disparity, where nodes exhibit varying homophily at both class and node levels; and 2) limited scalability, as many methods rely on costly whole-graph operations. To address them, we propose SAGAD, a Scalable and Adaptive framework for GAD. SAGAD precomputes multi-hop embeddings and applies reparameterized Chebyshev filters to extract low- and high-frequency information, enabling efficient training and capturing both homophilic and heterophilic patterns. To mitigate node-level homophily disparity, we introduce an Anomaly Context-Aware Adaptive Fusion, which adaptively fuses low- and high-pass embeddings using fusion coefficients conditioned on Rayleigh Quotient-guided anomalous subgraph structures for each node. To alleviate class-level disparity, we design a Frequency Preference Guidance Loss, which encourages anomalies to preserve more high-frequency information than normal nodes. SAGAD supports mini-batch training, achieves linear time and space complexity, and drastically reduces memory usage on large-scale graphs. Theoretically, SAGAD ensures asymptotic linear separability between normal and abnormal nodes under mild conditions. Extensive experiments on 10 benchmarks confirm SAGAD's superior accuracy and scalability over state-of-the-art methods.

Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), which play a crucial role in organizing and integrating web knowledge from diverse modalities. Although prior studies have made progress by multi-modal features fusion, three inherent limitations remain unresolved. First, instance-level feature fusion is misaligned with the pair-wise task format of MMEA. Second, joint representations often overlook modality-specific characteristics, resulting in insufficient alignment. Third, most existing methods rely solely on global features of modality. This may lead to the misalignment of entities that are similar yet distinct. To address above issues, we propose DMEA, a new decision-fusion-based framework. Specifically, we first design a multi-modal knowledge encoding module to extract both global and local features for different modalities and then introduce a multi-grained alignment module, which consists of two components: intra-modal alignment and cross-modal alignment. The former computes alignment scores between the global and local features of entity pairs within the same modality, while the latter leverages the complementarity across modalities to compute cross-modal alignment scores. Each score is regarded as an independent decision, and the final alignment judgment is made by integrating all decisions. Finally, we incorporate an intra-modal contrastive loss to obtain more discriminative embedding representations. DMEA achieves improvements of 13.2% and 14.8% in hit@1 over the state-of-the-art models on two benchmark datasets, FB15K-DB15K and FB15K-YAGO15K, respectively, validating the superiority of our framework.

Link Prediction (LP) is a crucial problem in graph-structured data. Graph Neural Networks (GNNs) have gained prominence in LP, with Graph AutoEncoders (GAEs) being a notable representation. However, our empirical findings reveal that GAEs’ LP performance suffers heavily from the long-tailed node degree distribution, i.e., low-degree nodes tend to exhibit inferior LP performance compared to high-degree nodes. What causes this degree-related bias, and how can it be mitigated? In this study, we demonstrate that the norm of node embeddings learned by GAEs exhibits variation among nodes with different degrees, underscoring its central significance in influencing the final performance of LP. Specifically, embeddings with larger norms tend to guide the decoder towards predicting higher scores for positive links and lower scores for negative links, thereby contributing to superior performance. This observation motivates us to improve GAEs’ LP performance on low-degree nodes by increasing their embedding norms, which can be implemented simply yet effectively by introducing additional self-loops into the training objective for low-degree nodes. This norm augmentation strategy can be seamlessly integrated into existing GAE methods with light computational cost. Extensive experiments on various datasets and GAE methods show the superior performance of norm-augmented GAEs.

Dynamic recommendation, focusing on modeling user preference from historical interactions and providing recommendations on current time, plays a key role in many personalized services. Recent works show that pre-trained dynamic graph neural networks (GNNs) can achieve excellent performance. However, existing methods by fine-tuning node representations at large scales demand significant computational resources. Additionally, the long-tail distribution of degrees leads to insufficient representations for nodes with sparse interactions, posing challenges for efficient fine-tuning. To address these issues, we introduce GraphSASA, a novel method for efficient fine-tuning in dynamic recommendation systems. GraphSASA employs test-time augmentation by leveraging the similarity of node representation distributions during hierarchical graph aggregation, which enhances node representations. Then it applies singular value decomposition, freezing the original vector matrix while focusing fine-tuning on the derived singular value matrices, which reduces the parameter burden of fine-tuning and improves the fine-tuning adaptability. Experimental results demonstrate that our method achieves state-of-the-art performance on three large-scale datasets.

Large language models (LLMs) have made remarkable strides, expanding their applications from casual dialogue to a wide spectrum of AI tasks. However, concerns about their reliability persist, particularly regarding their tendency to produce toxic content. In response, researchers have developed various toxicity benchmarks to evaluate LLM safety. Nevertheless, as LLMs scale and attack strategies grow more sophisticated, existing benchmarks fall short in assessing the safety of modern models. Addressing increasingly complex and diverse harmful inputs has become a major challenge. To mitigate these risks and leverage existing high-quality datasets, we propose a novel two-stage framework consisting of augmenting red teaming attack templates and generating a human preference dataset. First, we analyze existing red teaming methods, identifying key strategies that effectively exploit LLM vulnerabilities. Followed by augmenting high-quality red teaming attack templates using in-context learning and task-oriented prompt engineering. Then, we leverage the generated attack templates and existing toxicity datasets to generate diverse, high-quality toxic prompts across five threat scenarios: toxicity, stereotype bias, machine ethics, truthfulness, and privacy, intended to elicit toxic responses. To defend against these attacks, we design a Chain-of-Thought (CoT)-based safety guardrail, structured as toxic prompt, toxic response and safety prompt, to generate human preference responses across scenarios. Consequently, we construct the toxic preference dataset containing 7, 502 instances, each consisting of a toxic prompt, a toxic response and a human preference response. We fine-tune the Llama3-8B model on this dataset to enhance its robustness against red teaming attacks. Extensive experiments on five representative LLMs, including our fine-tuned model, demonstrate the effectiveness of our framework in both attack augmentation and human-aligned response generation.

Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate relationships and diverse relational semantics inherent in heterogeneous graph structures. However, the neighborhood-fetching latency incurred by structure dependency in HGNNs makes it challenging to deploy for latency-constrained applications that require fast inference. Inspired by recent GNN-to-MLP knowledge distillation frameworks, we introduce HG2M and HG2M+ to combine both HGNN’s superior performance and MLP’s efficient inference. HG2M directly trains student MLPs with node features as input and soft labels from teacher HGNNs as targets, and HG2M+ further distills reliable and heterogeneous semantic knowledge into student MLPs through reliable node distillation and reliable meta-path distillation. Experiments conducted on six heterogeneous graph datasets show that despite lacking structural dependencies, HG2Ms can still achieve competitive or even better performance than HGNNs and significantly outperform vanilla MLPs. Moreover, HG2Ms demonstrate a 379.24× speedup in inference over HGNNs on the large-scale IGB-3M-19 dataset, showcasing their ability for latency-sensitive deployments.

Attributed graph clustering, which aims to group the nodes of an attributed graph into disjoint clusters, has made promising advancements in recent years. However, most existing methods face challenges when applied to large graphs due to the expensive computational cost and high memory usage. In this paper, we introduce Scalable and Adaptive Spectral Embedding (SASE), a simple attributed graph clustering method devoid of parameter learning. SASE comprises three main components: node features smoothing via k-order simple graph convolution, scalable spectral clustering using random Fourier features, and adaptive order selection. With these designs, SASE not only effectively captures global cluster structures but also exhibits linear time and space complexity relative to the graph size. Empirical results demonstrate the superiority of SASE. For example, on the ArXiv dataset with 169K nodes and 1.17M edges, SASE achieves a 6.9% improvement in ACC and a 5.87× speedup compared to the runner-up, S3GC.

Graph clustering, which involves the partitioning of nodes within a graph into disjoint clusters, holds significant importance for numerous subsequent applications. Recently, contrastive learning, known for utilizing supervisory information, has demonstrated encouraging results in deep graph clustering. This methodology facilitates the learning of favorable node representations for clustering by attracting positively correlated node pairs and distancing negatively correlated pairs within the representation space. Nevertheless, a significant limitation of existing methods is their inadequacy in thoroughly exploring node-wise similarity. For instance, some hypothesize that the node similarity matrix within the representation space is identical, ignoring the inherent semantic relationships among nodes. Given the fundamental role of instance similarity in clustering, our research investigates contrastive graph clustering from the perspective of the node similarity matrix. We argue that an ideal node similarity matrix within the representation space should accurately reflect the inherent semantic relationships among nodes, ensuring the preservation of semantic similarities in the learned representations. In response to this, we introduce a new framework, Reliable Node Similarity Matrix Guided Contrastive Graph Clustering (NS4GC), which estimates an approximately ideal node similarity matrix within the representation space to guide representation learning. Our method introduces node-neighbor alignment and semantic-aware sparsification, ensuring the node similarity matrix is both accurate and efficiently sparse. Comprehensive experiments conducted on 8 real-world datasets affirm the efficacy of learning the node similarity matrix and the superior performance of NS4GC.

Automated program repair (APR) aims to fix software bugs automatically without human debugging efforts and plays a crucial role in software development and maintenance. Despite the recent significant progress in the number of fixed bugs, APR is still challenged by a long-standing overfitting problem (i.e., the generated patch is plausible but overfitting). Various techniques have thus been proposed to address the overfitting problem. Recently, researchers have employed BERT to extract code features, which are then used to train a classifier for patch correctness prediction, indicating the potential of such pre-trained models in reasoning about patch correctness. However, BERT is restricted to feature extraction for classifier training without benefiting from the training process, potentially generating sub-optimal vector representations for patched code snippets. In this paper, we propose APPT, a pre-trained model-based automated patch correctness assessment technique by both pre-training and fine-tuning. APPT adopts a pre-trained model as the encoder stack, followed by an LSTM stack and a deep learning classifier. More importantly, the pre-trained model is fine-tuned in conjunction with other components as a whole pipeline to fully adapt it specifically for reasoning about patch correctness. Although our idea is general and can be built on various existing pre-trained models, we have implemented APPT based on the BERT model. We conduct an extensive experiment on 1,183 Defects4J patches and the experimental results show that APPT achieves prediction accuracy of 79.7% and recall of 83.2%, outperforming the state-of-the-art technique CACHE by 4.3% and 6.7%. Our additional investigation on 49,694 real-world patches shows that APPT achieves the optimum performance (exceeding 99% in five common metrics for assessing patch classification techniques) compared with existing representation learning techniques. We further investigate the impact of each component and find that they all positively contribute to APPT, e.g., the fine-tuning process and the LSTM stack increase F1-score by 10.22% and 4.11%, respectively. We also prove that adopting advanced pre-trained models can further provide substantial advancement (e.g., GraphCodeBERT-based APPT improves BERT-based APPT by 2.8% and 3.3% in precision and AUC, respectively), highlighting the generalizability of APPT. Overall, our study highlights the promising future of fine-tuning pre-trained models to assess patch correctness and reduce the manual inspection effort of debugging experts when deploying APR tools in practice.

Federated Recommender Systems (FedRecs) are considered privacy-preserving techniques to collaboratively learn a recommendation model without sharing user data. Since all participants can directly influence the systems by uploading gradients, FedRecs are vulnerable to poisoning attacks of malicious clients. However, most existing poisoning attacks on FedRecs are either based on some prior knowledge or with less effectiveness. To reveal the real vulnerability of FedRecs, in this paper, we present a new poisoning attack method to manipulate target items' ranks and exposure rates effectively in the top-K recommendation without relying on any prior knowledge. Specifically, our attack manipulates target items' exposure rate by a group of synthetic malicious users who upload poisoned gradients considering target items' alternative products. We conduct extensive experiments with two widely used FedRecs (Fed-NCF and Fed-LightGCN) on two real-world recommendation datasets. The experimental results show that our attack can significantly improve the exposure rate of unpopular target items with extremely fewer malicious users and fewer global epochs than state-of-the-art attacks. In addition to disclosing the security hole, we design a novel countermeasure for poisoning attacks on FedRecs. Specifically, we propose a hierarchical gradient clipping with sparsified updating to defend against existing poisoning attacks. The empirical results demonstrate that the proposed defending mechanism improves the robustness of FedRecs.

The increasing data privacy concerns in recommendation systems have made federated recommendations attract more and more attention. Existing federated recommendation systems mainly focus on how to effectively and securely learn personal interests and preferences from their on-device interaction data. Still, none of them considers how to efficiently erase a user's contribution to the federated training process. We argue that such a dual setting is necessary. First, from the privacy protection perspective, "the right to be forgotten (RTBF)" requires that users have the right to withdraw their data contributions. Without the reversible ability, federated recommendation systems risk breaking data protection regulations. On the other hand, enabling a federated recommender to forget specific users can improve its robustness and resistance to malicious clients' attacks.

The marriage of federated learning and recommender system (FedRec) has been widely used to address the growing data privacy concerns in personalized recommendation services. In FedRecs, users’ attribute information and behavior data (i.e., user-item interaction data) are kept locally on their personal devices, therefore, it is considered a fairly secure approach to protect user privacy. As a result, the privacy issue of FedRecs is rarely explored. Unfortunately, several recent studies reveal that FedRecs are vulnerable to user attribute inference attacks, highlighting the privacy concerns of FedRecs. In this paper, we further investigate the privacy problem of user behavior data (i.e., user-item interactions) in FedRecs. Specifically, we perform the first systematic study on interaction-level membership inference attacks on FedRecs. An interaction-level membership inference attacker is first designed, and then the classical privacy protection mechanism, Local Differential Privacy (LDP), is adopted to defend against the membership inference attack. Unfortunately, the empirical analysis shows that LDP is not effective against such new attacks unless the recommendation performance is largely compromised. To mitigate the interaction-level membership attack threats, we design a simple yet effective defense method to significantly reduce the attacker’s inference accuracy without losing recommendation performance. Extensive experiments are conducted with two widely used FedRecs (Fed-NCF and Fed-LightGCN) on three real-world recommendation datasets (MovieLens-100K, Steam-200K, and Amazon Cell Phone), and the experimental results show the effectiveness of our solutions.

Automatic Program Repair (APR) aims at fixing buggy source code with less manual debugging efforts, which plays a vital role in improving software reliability and development productivity. Recent APR works have achieved remarkable progress via applying deep learning (DL), particularly neural machine translation (NMT) techniques. However, we observe that existing DL-based APR models suffer from at least two severe drawbacks: (1) Most of them can only generate patches for a single programming language, as a result, to repair multiple languages, we have to build and train many repairing models. (2) Most of them are developed offline. Therefore, they won’t function when there are new-coming requirements.

Question Generation (QG), as a challenging Natural Language Processing task, aims at generating questions based on given answers and context. Existing QG methods mainly focus on building or training models for specific QG datasets. These works are subject to two major limitations: (1) They are dedicated to specific QG formats (e.g., answer-extraction or multi-choice QG), therefore, if we want to address a new format of QG, a re-design of the QG model is required. (2) Optimal performance is only achieved on the dataset they were just trained on. As a result, we have to train and keep various QG models for different QG datasets, which is resource-intensive and ungeneralizable.

Question Generation (QG) is a challenging Natural Language Processing (NLP) task which aims at generating questions with given answers and context. There are many works incorporating linguistic features to improve the performance of QG. However, similar to traditional word embedding, these works normally embed such features with a set of trainable parameters, which results in the linguistic features not fully exploited. In this work, inspired by the recent achievements of text representation, we propose to utilize linguistic information via large pre-trained neural models. First, these models are trained in several specific NLP tasks in order to better represent linguistic features. Then, such feature representation is fused into a seq2seq based QG model to guide question generation. Extensive experiments were conducted on two benchmark Question Generation datasets to evaluate the effectiveness of our approach. The experimental results demonstrate that our approach outperforms the state-of-the-art QG systems, as a result, it significantly improves the baseline by 17.2% and 6.2% under the BLEU-4 metric on these two datasets, respectively.

Crowdsourced testing provides an effective way to deal with the problem of Android system fragmentation, as well as the application scenario diversity faced by Android testing. The generation of test requirements is a significant part of crowdsourced testing. However, manually generating crowdsourced testing requirements is tedious, which requires the issuers to have the domain knowledge of the Android application under test. To solve these problems, we have developed a tool named KARA, short for Knowledge Graph Aided Crowdsourced Requirements Generation for Android Testing. KARA first analyzes the result of automatic testing on the Android application, through which the operation sequences can be obtained. Then, the knowledge graph of the target application is constructed in a manner of pay-as-you-go. Finally, KARA utilizes knowledge graph and the automatic testing result to generate crowdsourced testing requirements with domain knowledge. Experiments prove that the test requirements generated by KARA are well understandable, and KARA can improve the quality of crowdsourced testing. The demo video can be found at https://youtu.be/kE-dOiekWWM.

The booming of big data makes the adoption of machine learning ubiquitous in the legal field. As we all know, a large amount of test data can better reflect the performance of the model, so the test data must be naturally expanded. In order to solve the high cost problem of labeling data in natural language processing, people in the industry have improved the performance of text classification tasks through simple data amplification techniques. However, the data amplification requirements in the judgment documents are interpretable and logical, as observed from CAIL2018 test data with over 200,000 judicial documents. Therefore, we have designed a test augmentation tool called TauJud specifically for generating more effective test data with uniform distribution over time and location for model evaluation and save time in marking data. The demo can be found at https://github.com/governormars/TauJud.

It is typically a manual, time-consuming, and tedious task of assigning bug reports to individual developers. Although some machine learning techniques are adopted to alleviate this dilemma, they are mainly focused on the open source projects, which use traditional repositories such as Bugzilla to manage their bug reports. With the boom of the mobile Internet, some new requirements and methods of software testing are emerging, especially the crowdsourced testing. Unlike the traditional channels, whose bug reports are often heavyweight, which means their bug reports are standardized with detailed attribute localization, bug reports tend to be lightweight in the context of crowdsourced testing. To exploit the differences of the bug reports assignment in the new settings, a unified bug reports assignment framework is proposed in this paper. This framework is capable of handling both the traditional heavyweight bug reports and the lightweight ones by (i) first preprocessing the bug reports and feature selections, (ii) then tuning the parameters that indicate the ratios of choosing different methods to vectorize bug reports, (iii) and finally applying classification algorithms to assign bug reports. Extensive experiments are conducted on three datasets to evaluate the proposed framework. The results indicate the applicability of the proposed framework, and also reveal the differences of bug report assignment between traditional repositories and crowdsourced ones.

In crowdsourced mobile application testing, crowd workers help developers perform testing and submit test reports for unexpected behaviors. These submitted test reports usually provide critical information for developers to understand and reproduce the bugs. However, due to the poor performance of workers and the inconvenience of editing on mobile devices, the quality of test reports may vary sharply. At times developers have to spend a significant portion of their available resources to handle the low-quality test reports, thus heavily decreasing their efficiency. In this paper, to help developers predict whether a test report should be selected for inspection within limited resources, we propose a new framework named TERQAF to automatically model the quality of test reports. TERQAF defines a series of quantifiable indicators to measure the desirable properties of test reports and aggregates the numerical values of all indicators to determine the quality of test reports by using step transformation functions. Experiments conducted over five crowdsourced test report datasets of mobile applications show that TERQAF can correctly predict the quality of test reports with accuracy of up to 88.06% and outperform baselines by up to 23.06%. Meanwhile, the experimental results also demonstrate that the four categories of measurable indicators have positive impacts on TERQAF in evaluating the quality of test reports.

DevOps is a new approach to drive a seamless Application (App) cycle from development to delivery. As a critical part to promote the successful implementation of DevOps, testing can significantly improve team productivity and reliably deliver user experience. However, it is difficult to use traditional testing to cover diverse mobile phones, network environments, operating systems, and so on. Hence, many large companies crowdsource their App testing tasks to workers from open platforms. In crowdsourced testing, test reports submitted by workers may be highly redundant, and their quality may vary sharply. Meanwhile, multi-bug test reports may be submitted, and their root causes are hard to diagnose. Hence, it is a time-consuming and tedious task for developers to manually inspect these test reports. To help developers address the above challenges, we issue the new problem of Fuzzy Clustering Test Reports (FULTER). Aiming to resolve FULTER, a series of barriers need to be overcome. In this study, we propose a new framework named Test Report Fuzzy Clustering Framework (TERFUR) by aggregating redundant and multi-bug test reports into clusters to reduce the number of inspected test reports. First, we construct a filter to remove invalid test reports to break through the invalid barrier . Then, a preprocessor is built to enhance the descriptions of short test reports to break through the uneven barrier . Last, a two-phase merging algorithm is proposed to partition redundant and multi-bug test reports into clusters that can break through the multi-bug barrier . Experimental results over 1,728 test reports from five industrial Apps show that TERFUR can cluster test reports by up to 78.15% in terms of AverageP , 78.41% in terms of AverageR , and 75.82% in terms of AverageF1 and outperform comparative methods by up to 31.69%, 33.06%, and 24.55%, respectively. In addition, the effectiveness of TERFUR is validated in prioritizing test reports for manual inspection.

With the process of the information openness and the development of Internet technology, judicial data begin to enter the public view, and the carrier of that is the referee document, as referee document almost reflect all information of cases. Everyone is a social media content producer and consumer, which on behalf of public's opinion about the law, and it has made the legal significance not only limited to the professional field, but also includes social cognitive meanings. So, Digging into the relationship between professional legal meaning and social cognition has become an important issue. We use the knowledge graph to construct the relationship network between social media and law entities of professional legal data, and introduce the related methods of knowledge graph.

Document clustering (or text clustering) is the application of cluster analysis to textual documents. It has applications in automatic document organization, topic extraction and fast information retrieval or filtering. At the same time, there are still many challenges, for example the accuracy of clustering needs to be improved. In this regard, the process of cluster correction becomes the object of analysis. In this paper, we focus on the polysemy and synonymy issue in clustering process. Polysemy represents the ambiguity of an individual word or phrase that can be used (in different contexts) to express two or more different meanings. However, synonymy is the semantic relation that holds between two or more words that can (in a given context) express the same meaning. These two conditions will affect our results of clustering. In order that, we use bag of words model to distinguish contexts of the same words and word2vec to re-cluster word with the similar meaning. Cosine similarity is also use to measure of similarity between two nonzero vectors in these two model.

In this paper, we propose a clustering framework to analyze the log files generated along crowdsourcing mobile application testing. Our object is to automatically identify the type of testing work that the worker is performing as to reduce the work of developers clustering the test reports. By taking full data information of the log files, we establish the hierarchy of the testing data. Through the application of data processing and stream clustering methods, we accomplish the static mining and dynamic division of the test stream data. Experiments on a crowdsourcing mobile application testing dataset the efficacy of our approach.

To improve software quality, developers often open a bug repository and allow users to find bugs, describe bugs in the form of bug reports and submit bug reports to the repository.Based on the description, testers assign a priority to each bug report.In the beginning the process of priority assignment is performed manually.With the increasing amount of bug reports, researchers introduced classification methods to assign priorities automatically with all the features considered.In this paper feature selection methods are introduced to improve the effect of bug report prioritization using classification models.The experimental results show that feature selection based on Information Gain and Pearson Correlation can improve the precision and recall for bug report prioritization on two models, i.e., SVM and Naive Bayes.

The turn-by-turn directions provided in existing navigation applications are exclusively derived from underlying road network topology information, i.e., the connectivity of edges to each other. Therefore, the turn-by-turn directions are simplified as metric translation of physical world (e.g. distance/time to turn) to spoken language. Such translation - that ignores human cognition of the geographic space - is often verbose and redundant for the drivers who have knowledge about the geographical areas. In this paper, we study a Personalized RoutE Guidance System dubbed PaRE - with which the goal is to generate more customized and intuitive directions based on user generated content. PaRE utilizes a wealth of user generated historical trajectory data to extract namely "landmarks" (e.g., point of interests or intersections) and frequently visited routes between them from the road network. The extracted information is used to obtain cognitive customized directions for each user. We formalize this task as a problem of finding the optimal partition for a given route that maximizes the familiarity while minimizing the number of segments in the partition, and propose two efficient algorithms to solve it. For empirical study, we apply our solution to both real and synthetic trajectory datasets to evaluate the performance and effectiveness of PaRE.

Manually reading all the product reviews to find a satisfying item is not only labor-intensive, but also tedious for the consumers.In this paper, we propose a feature-opinion mining approach to automatically summarize the reviews.Specifically, in our approach we first utilize a regression model to generate sentiment word, including phrase and its sentiment weight, then extract feature based on the dependency relationship between feature word and sentiment word, and finally we assign score to feature according to the dependency relationship.The experimental results demonstrate that our approach can effectively mine the featureopinion from reviews.

Combinatorial testing is widely used to detect failures caused by interactions among parameters for its efficiency and effectiveness.Fault localization plays an important role in this testing technique.And minimal failure-causing schema is the root cause of failure.In this paper, an efficient algorithm, which identifies minimal failure-causing schemas from existing failed test cases and passed test cases, is proposed to replace the basic algorithm with worse time performance.Time complexity of basic and improved algorithms is calculated and compared.The result shows that the method that utilizes the differences between failed test cases and passed test cases is better than the method that only uses the sub-schemas of those test cases.

Time factor has been widely applied into a wide range of data mining areas, such as social network and information retrieval.The main idea of taking time factor into consideration is that human activities may have some relations to time pattern.However, little attention has been pulled on the study of time factor in the area of software engineering.In this paper, we endeavour to explore to what extent time factor affects the prioritization of bug reports, a specified while important task in software engineering.Specifically, we test four time factors that may have some influence on this task, which are time of day, normal time, day of week, and days to major version.After the validation of relatedness of all these factors, we conduct an extensive set of experiments on two datasets to verify the effectiveness of these factors.The experimental results demonstrate that we can effectively improve the results by metrics of both Precision and Recall, on two classical models, i.e., the SVM model and Naive Bayes model.

The manual reading of all the product reviews to find a satisfying item is not only labor-intensive, but also tedious for the consumers. In this paper, we propose a feature-opinion mining approach to automatically summarize the reviews, which is based on dependency parsing. Specifically, in our approach we first utilize a regression model to generate sentiment word, including phrase and its sentiment weight, and then we extract the feature based on the dependency relationship between feature word and sentiment word, finally we assign a score to the feature according to the dependency relationship. The experimental results demonstrate that our approach can effectively mine the feature-opinion from reviews.

Semantic tags of points of interest (POIs) are a crucial prerequisite for location search, recommendation services, and data cleaning. However, most POIs in location-based social networks (LBSNs) are either tag-missing or tag-incomplete. This article aims to develop semantic annotation techniques to automatically infer tags for POIs. We first analyze two LBSN datasets and observe that there are two types of tags, category-related ones and sentimental ones, which have unique characteristics. Category-related tags are hierarchical, whereas sentimental ones are category-aware. All existing related work has adopted classification methods to predict high-level category-related tags in the hierarchy, but they cannot apply to infer either low-level category tags or sentimental ones. In light of this, we propose a latent-class probabilistic generative model, namely the spatial-temporal topic model (STM), to infer personal interests, the temporal and spatial patterns of topics/semantics embedded in users’ check-in activities, the interdependence between category-topic and sentiment-topic, and the correlation between sentimental tags and rating scores from users’ check-in and rating behaviors. Then, this learned knowledge is utilized to automatically annotate all POIs with both category-related and sentimental tags in a unified way. We conduct extensive experiments to evaluate the performance of the proposed STM on a real large-scale dataset. The experimental results show the superiority of our proposed STM, and we also observe that the real challenge of inferring category-related tags for POIs lies in the low-level ones of the hierarchy and that the challenge of predicting sentimental tags are those with neutral ratings.