In asynchronous software development, a single change often requires synchronized updates across multiple files, posing a significant challenge for collaborative code generation. Current approaches often overlook the implicit collaborative knowledge embedded in the project’s evolutionary history. To bridge this gap, we propose EvoCoGen, a framework that leverages a Weighted Evolutionary Coupling Graph (WECG). Unlike static analysis, which misses implicit dependencies, and traditional frequency-based methods prone to noise, we introduce Time-Weighted Mutual Information (TWMI). This metric integrates commit recency, focus, and statistical independence to robustly model co-evolution. WECG serves as a dynamic knowledge base, guiding Large Language Models (LLMs) to generate coherent cross-file modifications. Experiments on six open-source and industrial projects reveal that coupling effectiveness is contingent on "commit culture": TWMI excels in projects with skewed/heavy-tailed distributions via its denoising capability, while traditional methods suit stable environments. Moreover, WECG-guided LLMs consistently equal or outperform baselines lacking evolutionary context, particularly excelling in capturing implicit dependencies invisible to static tools. This work offers a socio-technical perspective: by making implicit coordination explicit, LLMs are empowered to not only "understand code" but also "understand collaboration".

Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency. This paper will delve into utilizing LLMs for code generation in private libraries, as they are widely employed in everyday programming. Despite their remarkable capabilities, generating such private APIs poses a formidable conundrum for LLMs, as they inherently lack exposure to these private libraries during pre-training. To address this challenge, we propose a novel framework that emulates the process of programmers writing private code. This framework comprises two modules: APIFinder first retrieves potentially useful APIs from API documentation; and APICoder then leverages these retrieved APIs to generate private code. Specifically, APIFinder employs vector retrieval techniques and allows user involvement in the retrieval process. For APICoder, it can directly utilize off-the-shelf code generation models. To further cultivate explicit proficiency in invoking APIs from prompts, we continuously pre-train a reinforced version of APICoder, named CodeGenAPI. Our goal is to train the above two modules on vast public libraries, enabling generalization to private ones. Meanwhile, we create four private library benchmarks, including TorchDataEval, TorchDataComplexEval, MonkeyEval, and BeatNumEval, and meticulously handcraft test cases for each benchmark to support comprehensive evaluations. Numerous experiments on the four benchmarks consistently affirm the effectiveness of our approach. Furthermore, deeper analysis is also conducted to glean additional insights.

Code large language models (Code LLMs) have demonstrated remarkable performance in code generation. Nonetheless, most existing works focus on boosting code LLMs from the perspective of programming capabilities, while their natural language capabilities receive less attention. To fill this gap, we thus propose a novel framework, comprising two modules: AttentionExtractor, which is responsible for extracting key phrases from the user's natural language requirements, and AttentionCoder, which leverages these extracted phrases to generate target code to solve the requirement. This framework pioneers an innovative idea by seamlessly integrating code LLMs with traditional natural language processing tools. To validate the effectiveness of the framework, we craft a new code generation benchmark, called MultiNL-H, covering five natural languages. Extensive experimental results demonstrate the effectiveness of our proposed framework.

In vertical federated learning (VFL), commercial entities collaboratively train a model while preserving data privacy. However, a malicious participant's poisoning attack may degrade the performance of this collaborative model. The main challenge in achieving the poisoning attack is the absence of access to the server-side top model, leaving the malicious participant without a clear target model. To address this challenge, we introduce an innovative end-to-end poisoning framework P-GAN. Specifically, the malicious participant initially employs semi-supervised learning to train a surrogate target model. Subsequently, this participant employs a GAN-based method to produce adversarial perturbations to degrade the surrogate target model's performance. Finally, the generator is obtained and tailored for VFL poisoning. Besides, we develop an anomaly detection algorithm based on a deep auto-encoder (DAE), offering a robust defense mechanism to VFL scenarios. Through extensive experiments, we evaluate the efficacy of P-GAN and DAE, and further analyze the factors that influence their performance.

In the era of code large language models (code LLMs), data engineering plays a pivotal role during the instruction fine-tuning phase. To train a versatile model, previous efforts devote tremendous efforts to crafting instruction data that covers all the downstream scenarios. Nonetheless, this will incur significant expenses in data construction and model training. Therefore, this paper introduces CODEM, a novel data construction strategy, which can efficiently train a versatile model using less data via our newly proposed ability matrix. CODEM uses ability matrix to decouple code LLMs' abilities into two dimensions, constructing a lightweight training corpus that only covers a subset of target scenarios. Extensive experiments on HumanEvalPack and MultiPL-E reveal that code LLMs can combine the single-dimensional abilities to master composed abilities, validating the effectiveness of CODEM.

The task of code generation aims to generate code solutions based on given programming problems. Recently, code large language models (code LLMs) have shed new light on this task, owing to their formidable code generation capabilities. While these models are powerful, they seldom focus on further improving the accuracy of library-oriented API invocation. Nonetheless, programmers frequently invoke APIs in routine coding tasks. In this paper, we aim to enhance the proficiency of existing code LLMs regarding API invocation by mimicking analogical learning, which is a critical learning strategy for humans to learn through differences among multiple instances. Motivated by this, we propose a simple yet effective approach, namely DiffCoder, which excels in API invocation by effectively training on the differences (diffs) between analogical code exercises. To assess the API invocation capabilities of code LLMs, we conduct experiments on seven existing benchmarks that focus on mono-library API invocation. Additionally, we construct a new benchmark, namely PanNumEval, to evaluate the performance of multi-library API invocation. Extensive experiments on eight benchmarks demonstrate the impressive performance of DiffCoder. Furthermore, we develop a VSCode plugin for DiffCoder, and the results from twelve invited participants further verify the practicality of DiffCoder.

The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task.

Vertical federated learning (VFL) enables multiple parties to collaboratively train a model while preserving privacy. However, recent studies have raised concerns about the susceptibility of VFL models, including those using logistic regression and neural networks, to feature inference attacks. Meanwhile, the non-differentiable characteristics of decision tree ensembles make conducting such attacks impractical. To address this challenge, we introduce a feature inference attack framework FIA-TE tailored for decision tree ensembles, including gradient boosted decision trees (GBDT) and random forest. Specifically, we distill the knowledge from trees into neural networks by leaf embedding and structure distillation to create a targeted model for the inference attack. We then employ a generative model based on the deconvolutional network for capturing correlation features and reconstructing the target features. Through extensive experiments on table and image data, we evaluate the effectiveness of our framework and provide an analysis of potential influencing factors.

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been released to evaluate issue resolving capabilities of large language models (LLMs), but has so far only focused on Python version. However, supporting more programming languages is also important, as there is a strong demand in industry. As a first step toward multilingual support, we have developed a Java version of SWE-bench, called SWE-bench-java. We have publicly released the dataset, along with the corresponding Docker-based evaluation environment and leaderboard, which will be continuously maintained and updated in the coming months. To verify the reliability of SWE-bench-java, we implement a classic method SWE-agent and test several powerful LLMs on it. As is well known, developing a high-quality multi-lingual benchmark is time-consuming and labor-intensive, so we welcome contributions through pull requests or collaboration to accelerate its iteration and refinement, paving the way for fully automated programming.

The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. Thanks to the rapid development of pre-training techniques, surging large language models are being proposed for code, sparking the advances in NL2Code. To facilitate further research and applications in this field, in this paper, we present a comprehensive survey of 27 existing large language models for NL2Code, and also review benchmarks and metrics. We provide an intuitive comparison of all existing models on the HumanEval benchmark. Through in-depth observation and analysis, we provide some insights and conclude that the key factors contributing to the success of large language models for NL2Code are "Large Size, Premium Data, Expert Tuning". In addition, we discuss challenges and opportunities regarding the gap between models and humans. We also create a website https://nl2code.github.io to track the latest progress through crowd-sourcing. To the best of our knowledge, this is the first survey of large language models for NL2Code, and we believe it will contribute to the ongoing development of the field.

Integrating social relations into recommendation is an effective way to mitigate data sparsity. Most social recommendation methods encode user representations from a unified graph that includes user-user and user-item relations. Due to the enriched relations on this graph, a large fraction of users are aware of each other within only a few hops, and the user representations generated by existing methods may encode the information received from a large number of neighbors. Thus, many user representations are enforced to be too similar, which hinders modeling fine-grained user interest. Here, we name this phenomenon as user representation collapse. To address this problem, in this paper we propose a robust user representation learning method named RobustSR with social regularization and multi-view contrastive learning, which aim to enhance the model’s awareness of relation informativeness and the discriminativeness of user representations, respectively. Concretely, the social regularization mechanism encourages the model to learn from the relation importance weights derived from graph topologies, which helps recognize important observed relations meanwhile mining potential useful relations. To enhance the discriminativeness of user representations, we further perform multi-view contrastive learning between collaborative and social-enhanced user representations. Extensive experiments on four benchmark datasets show that RobustSR effectively alleviates user representation collapse and improves recommendation performance. Our code is deposited at https://github.com/paulpig/RobustSR.

The article discusses the interconnected fields of computing and machine learning, and their impact on various areas such as energy, economics, indoor positioning, and business. Computing provides the foundation for data processing and storage, while machine learning enables algorithms and models to learn from data and make predictions. These advancements have revolutionized how we approach complex problems and opened up new avenues for research and innovation. The article highlights the potential of computing and data science to solve complex problems and the importance of staying up-to-date with the latest developments.

To adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample generation framework was constructed for the VFL architecture.A white-box adversarial attack in the VFL was implemented by extending the centralized machine learning adversarial sample generation algorithm with different policies such as L-BFGS, FGSM, and C＆amp;W.By introducing deep convolutional generative adversarial network (DCGAN), an adversarial sample generation algorithm named VFL-GASG was designed to address the problem of universality in the generation of adversarial perturbations.Hidden layer vectors were utilized as local prior knowledge to train the adversarial perturbation generation model, and through a series of convolution-deconvolution network layers, finely crafted adversarial perturbations were produced.Experiments show that VFL-GASG can maintain a high attack success while achieving a higher generation efficiency, robustness, and generalization ability than the baseline algorithm, and further verify the impact of relevant settings for adversarial attacks.

Incorporating knowledge graph into recommendation is an effective way to alleviate data sparsity. Most existing knowledge-aware methods usually perform recursive embedding propagation by enumerating graph neighbors. However, the number of nodes' neighbors grows exponentially as the hop number increases, forcing the nodes to be aware of vast neighbors under this recursive propagation for distilling the high-order semantic relatedness. This may induce more harmful noise than useful information into recommendation, leading the learned node representations to be indistinguishable from each other, that is, the well-known over-smoothing issue. To relieve this issue, we propose a Hierarchical and CONtrastive representation learning framework for knowledge-aware recommendation named HiCON. Specifically, for avoiding the exponential expansion of neighbors, we propose a hierarchical message aggregation mechanism to interact separately with low-order neighbors and meta-path-constrained high-order neighbors. Moreover, we also perform cross-order contrastive learning to enforce the representations to be more discriminative. Extensive experiments on three datasets show the remarkable superiority of HiCON over state-of-the-art approaches. The code is available now(1).

OBJECTIVE:To explore the correlation between diagnostic information of tongue and gastroscopy results of patients with chronic gastritis.METHODS:Frequent pattern growth (FP-Growth), SPSS Modeler was used to analyze the correlation rules between the image information of tongue parameters and the characteristics of the stomach and duodenum seen under gastroscopy.RESULTS:Ranking in order of confidence: cyanotic tongue, slippery fur, yellow fur and spotted tongue were sequently associated with both gastric antrum mucosal hyperemia or edema and gastric antrum mucosal erythema/macula. L, one value of tongue coating color, which counted among (30, 60), tooth-marked tongue and b, one value of tongue coating color, which counted in the range of (5, 20) were sequently associated with gastric antrum mucosal erythema /macula. A, one value of tongue body color, which counted in the range of (0, 20), was related to both gastric antrum mucosal hyperemia or edema and gastric antrum mucosal erythema /macula. a, one value of tongue coating color, which counted in the range of (15, 35), was associated with gastric antrum mucosal erythema / macula. There are a total of 9 strong correlation rules.CONCLUSIONS:Cyanotic tongue, slippery fur, yellow fur, the CIE Lab value of tongue coating, a, the value of tongue body color, spotted tongue, and tooth-marked tongue are all related to the gastric antrum mucosal hyperemia or edema and gastric antrum mucosal erythema / macula. The conditions of gastric mucosa could be predicted by the examination of the above related image information of tongue.

With the rapid development of pre-training techniques, a number of language models have been pre-trained on large-scale code corpora and perform well in code generation. In this paper, we investigate how to equip pre-trained language models with the ability of code generation for private libraries. In practice, it is common for programmers to write code using private libraries. However, this is a challenge for language models since they have never seen private APIs during training. Motivated by the fact that private libraries usually come with elaborate API documentation, we propose a novel framework with two modules: the APIRetriever finds useful APIs, and then the APICoder generates code using these APIs. For APIRetriever, we present a dense retrieval system and also design a friendly interaction to involve uses. For APICoder, we can directly use off-the-shelf language models, or continually pre-train the base model on a code corpus containing API information. Both modules are trained with data from public libraries and can be generalized to private ones. Furthermore, we craft three benchmarks for private libraries, named TorchDataEval, MonkeyEval, and BeatNumEval. Experimental results demonstrate the impressive performance of our framework.

[目的]探讨科技论文出版全生命周期的安全问题与解决措施,为加强保护科技论文中的涉密信息提供参考和借鉴.[方法]从科技论文出版全生命周期视角出发,分析在作者选题策划、作者单位审查、编辑部审稿和涉密材料销毁4个阶段中存在的潜在安全问题,并给予建设性的意见与对策.[结果]为确保科技论文出版全生命周期的安全性,作者需提高信息安全意识,作者单位需划定安全保密的等级,并且编辑部需培养兼顾专业性与保密安全意识的审稿人员.审稿人员需树立信息安全意识,妥善处理出版过程中的涉密材料.[结论]随着科技论文的全面网络化,科技论文出版面临严峻的信息安全挑战.从全生命周期角度出发分析科技论文出版过程中面临的安全问题,探讨相应的对策,可预防在科技论文出版过程中泄露敏感信息与情报的问题.

红外热成像技术可以直观反映物体的热分布并形成图像,通过观察人体表面的温度场以揣测分析机体内在状况和变化,正是中医"司外揣内"思维方法的具体体现.目前,红外热成像技术已广泛用于中医各领域研究中,为中医整体观提供了可量化、可视化数据支持.文章对红外热成像技术在中医基础理论与临证辨识等方面的应用进行梳理,对进一步研究提出参考性意见.

Knowledge Graph Question Answering (KGQA) is a challenging task that aims to obtain the entities from the given Knowledge Graph (KG) to answer the user's natural language questions. Most existing studies are focused on the traditional KGQA task, where the test distribution is the same as the training distribution over questions. In contrast, few efforts have been made to explore the zero-shot KGQA task. Logically, the existing models for the traditional KGQA task naturally show poor performance on the zero-shot setting. It is a non-trivial task to migrate the off-the-shelf zero-shot solutions in other common tasks to KGQA since an intrinsical gap exists between other common tasks and the KGQA task under the zero-shot settings. Furthermore, we observed that Similar Questions tend to have Similar Logic forms. Motivated by this, we propose a simple yet effective framework S(2)QL. In detail, we first elaborately devise three similarity measurement units to category the user's questions. Then based on the Similarity Relation Graph (SRG) constructed by the above similarity measurement units, we devise a retrieval augmented strategy to further answer arduous zero-shot questions with its retrieved similar questions. Extensive experiments on the GrailQA and WebQSP benchmarks demonstrate that our approach is more effective than a number of competitive KGQA baselines on the zero-shot setting.

The Question Answering over Knowledge Graph (KGQA) task seeks entities (answers) from the Knowledge Graph (KG) in order to answer natural language questions. In practice, KG is often incomplete, with numerous missing links and nodes. With such an incomplete KG, it is tricky to use the semantics inside the KG to get the golden answers, particularly for complex questions. Some current efforts concentrate on using external corpora to overcome KG sparsity; however, identifying and obtaining the corpora is challenging. Other types of work aim to leverage the pre-trained embeddings to resolve the issue but perform slightly worse on complex questions involving numerous triple facts in KG. To address the aforementioned problems, we present a framework CAPKGQA, which transforms Complex KGQA into an n-Ary link Prediction task capable of explicitly modeling complex questions. Furthermore, previous methods also suffer from incomplete KG throughout the candidate answer generation phase. Therefore, we devise an embedding-based retrieval strategy to extract more reliable candidate answers from incomplete KG. Extensive experiments reveal that our approach beats the state-of-the-art models on incomplete and complex KGQA tasks by a significant margin.