Searcharxiv⌕ Search

arXiv subjects

Shanshan Li

Publications and source records attributed to Shanshan Li.

At least 37 records · Page 2Linked to original sources
arXiv2024

Lagrangian Mean Curvature Flow in Pseudo-Euclidean Space II

In this paper, we consider the mean curvature flow of entire Lagrangian graphs with initial data in the pseudo-Euclidean space, which is related to the special Lagrangian parabolic equation. We show that the parabolic equation \eqref{11} has a smooth solution $u(x,t)$ for three corresponding nonlinear equations between the Monge-Amp$\grave{e}$re type equation($τ=0$) and the special Lagrangian parabolic equation($τ=\fracπ{2}$). Furthermore, we get the bound of $D^lu$, $l=\{3,4,5,\cdots\}$ for $τ=\fracπ{4}$ and the decay estimates of the higher order derivatives when $0<τ<\fracπ{4}$ and $\fracπ{4}<τ<\fracπ{2}$. We also prove that $u(x,t)$ converges to smooth self-expanding solutions of \eqref{12}.

math.DG↗
arXiv2024

Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation

Retrieval-augmented code generation utilizes Large Language Models as the generator and significantly expands their code generation capabilities by providing relevant code, documentation, and more via the retriever. The current approach suffers from two primary limitations: 1) information redundancy. The indiscriminate inclusion of redundant information can result in resource wastage and may misguide generators, affecting their effectiveness and efficiency. 2) preference gap. Due to different optimization objectives, the retriever strives to procure code with higher ground truth similarity, yet this effort does not substantially benefit the generator. The retriever and the generator may prefer different golden code, and this gap in preference results in a suboptimal design. Additionally, differences in parameterization knowledge acquired during pre-training result in varying preferences among different generators. To address these limitations, in this paper, we propose RRG (Retrieve, Refactor, Generate), a novel framework for effective and efficient code generation. This framework introduces a code refactorer module between the retriever and the generator to bridge them. The refactoring process transforms the raw retrieved code into a more concise, efficient, and model-friendly version. It eliminates redundant information and noise, reducing the input length. Consequently, the generator receives higher-quality context, enabling it to produce more accurate results with lower inference costs. We conducted comprehensive experiments on multiple datasets. In the experiments, we confirmed the existence of a preference gap between the retriever and the generator, and RRG effectively bridges this gap. Specifically, RRG achieved significant performance improvements, with increases of up to 28% on EM, 13% on BLEU, and 6.8% on CodeBLEU.

cs.SE↗
arXiv2024

A physical model for radio and X-ray correlation in black hole X-ray binaries

A tight correlation between the radio and X-ray emission in the hard state of black hole X-ray binaries (BHXRBs) indicates an intrinsic disc-jet connection in stellar black hole accretion systems, though the detailed physics processes at work are still quite unclear. A hot accretion flow is suggested to match the outer cold thin disc at a certain radius in the hard state, which may vary with the accretion rate. In this work, we assume that the magnetic field generated in the outer thin disc is advected inwards by the inner hot accretion flow, which is substantially enhanced near the BH. Such a strong field threading the horizon of a spinning BH is responsible for launching relativistic jets in BHXRBs via the Blandford-Znajek mechanism. Thus, both the jet power and the X-ray emission increase with the mass accretion rate, and we find that our model calculations are able to reproduce the observed radio/X-ray correlation quantitatively. For some individual BHXRBs, the slopes of the radio/X-ray correlations become steeper when the sources are brighter. Our model calculations show that this feature is due to the transition of the outer disc with gas pressure dominated to radiation pressure dominated, which leads to different accretion rate dependence of the field strength in the outer disc.

astro-ph.HE↗
arXiv2024

Detecting Build Dependency Errors in Incremental Builds

Incremental and parallel builds performed by build tools such as Make are the heart of modern C/C++ software projects. Their correct and efficient execution depends on build scripts. However, build scripts are prone to errors. The most prevalent errors are missing dependencies (MDs) and redundant dependencies (RDs). The state-of-the-art methods for detecting these errors rely on clean builds (i.e., full builds of a subset of software configurations in a clean environment), which is costly and takes up to multiple hours for large-scale projects. To address these challenges, we propose a novel approach called EChecker to detect build dependency errors in the context of incremental builds. The core idea of EChecker is to automatically update actual build dependencies by inferring them from C/C++ pre-processor directives and Makefile changes from new commits, which avoids clean builds when possible. EChecker achieves higher efficiency than the methods that rely on clean builds while maintaining effectiveness. We selected 12 representative projects, with their sizes ranging from small to large, with 240 commits (20 commits for each project), based on which we evaluated the effectiveness and efficiency of EChecker. We compared the evaluation results with a state-of-the-art build dependency error detection tool. The evaluation shows that the F-1 score of EChecker improved by 0.18 over the state-of-the-art method. EChecker increases the build dependency error detection efficiency by an average of 85.14 times (with the median at 16.30 times). The results demonstrate that EChecker can support practitioners in detecting build dependency errors efficiently.

cs.SE↗
arXiv2024

SPT: Spectral Transformer for Red Giant Stars Age and Mass Estimation

The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell diagram, while asteroseismology, though more precise, requires high-precision, long-term observations. In response to these challenges, we developed a novel framework, Spectral Transformer (SPT), to predict the age and mass of red giants aligned with asteroseismology from their spectra. A key component of SPT, the Multi-head Hadamard Self-Attention mechanism, designed specifically for spectra, can capture complex relationships across different wavelength. Further, we introduced a Mahalanobis distance-based loss function to address scale imbalance and interaction mode loss, and incorporated Monte Carlo dropout for quantitative analysis of prediction uncertainty.Trained and tested on 3,880 red giant spectra from LAMOST, the SPT achieved remarkable age and mass estimations with average percentage errors of 17.64% and 6.61%, respectively, and provided uncertainties for each corresponding prediction. The results significantly outperform those of traditional machine learning algorithms and demonstrate a high level of consistency with asteroseismology methods and isochrone fitting techniques. In the future, our work will leverage datasets from the Chinese Space Station Telescope and the Large Synoptic Survey Telescope to enhance the precision of the model and broaden its applicability in the field of astronomy and astrophysics.

astro-ph.SR↗
arXiv2023

Image Restoration with Point Spread Function Regularization and Active Learning

Large-scale astronomical surveys can capture numerous images of celestial objects, including galaxies and nebulae. Analysing and processing these images can reveal intricate internal structures of these objects, allowing researchers to conduct comprehensive studies on their morphology, evolution, and physical properties. However, varying noise levels and point spread functions can hamper the accuracy and efficiency of information extraction from these images. To mitigate these effects, we propose a novel image restoration algorithm that connects a deep learning-based restoration algorithm with a high-fidelity telescope simulator. During the training stage, the simulator generates images with different levels of blur and noise to train the neural network based on the quality of restored images. After training, the neural network can directly restore images obtained by the telescope, as represented by the simulator. We have tested the algorithm using real and simulated observation data and have found that it effectively enhances fine structures in blurry images and increases the quality of observation images. This algorithm can be applied to large-scale sky survey data, such as data obtained by LSST, Euclid, and CSST, to further improve the accuracy and efficiency of information extraction, promoting advances in the field of astronomical research.

astro-ph.IM↗
arXiv2023

Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation

Large language models (LLMs) have showcased remarkable prowess in code generation. However, automated code generation is still challenging since it requires a high-level semantic mapping between natural language requirements and codes. Most existing LLMs-based approaches for code generation rely on decoder-only causal language models often treate codes merely as plain text tokens, i.e., feeding the requirements as a prompt input, and outputing code as flat sequence of tokens, potentially missing the rich semantic features inherent in source code. To bridge this gap, this paper proposes the "Semantic Chain-of-Thought" approach to intruduce semantic information of code, named SeCoT. Our motivation is that the semantic information of the source code (\eg data flow and control flow) describes more precise program execution behavior, intention and function. By guiding LLM consider and integrate semantic information, we can achieve a more granular understanding and representation of code, enhancing code generation accuracy. Meanwhile, while traditional techniques leveraging such semantic information require complex static or dynamic code analysis to obtain features such as data flow and control flow, SeCoT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (i.e., in-context learning), while being generalizable and applicable to challenging domains. While SeCoT can be applied with different LLMs, this paper focuses on the powerful GPT-style models: ChatGPT(close-source model) and WizardCoder(open-source model). The experimental study on three popular DL benchmarks (i.e., HumanEval, HumanEval-ET and MBPP) shows that SeCoT can achieves state-of-the-art performance, greatly improving the potential for large models and code generation.

cs.CL↗
arXiv2023

At Which Training Stage Does Code Data Help LLMs Reasoning?

Large Language Models (LLMs) have exhibited remarkable reasoning capabilities and become the foundation of language technologies. Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning. To this end, this paper systematically explores the impact of code data on LLMs at different stages. Concretely, we introduce the code data at the pre-training stage, instruction-tuning stage, and both of them, respectively. Then, the reasoning capability of LLMs is comprehensively and fairly evaluated via six reasoning tasks in five domains. We critically analyze the experimental results and provide conclusions with insights. First, pre-training LLMs with the mixture of code and text can significantly enhance LLMs' general reasoning capability almost without negative transfer on other tasks. Besides, at the instruction-tuning stage, code data endows LLMs the task-specific reasoning capability. Moreover, the dynamic mixing strategy of code and text data assists LLMs to learn reasoning capability step-by-step during training. These insights deepen the understanding of LLMs regarding reasoning ability for their application, such as scientific question answering, legal support, etc. The source code and model parameters are released at the link:~\url{https://github.com/yingweima2022/CodeLLM}.

cs.CL↗
arXiv2023

One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization

As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks and models. However, we find that multilingual fine-tuning leads to performance degradation on recent models UniXcoder and CodeT5. To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it. Updating only 0.6\% of the overall parameters compared to full-model fine-tuning for each programming language, adapter tuning yields consistent improvements on code search and summarization tasks, achieving state-of-the-art results. In addition, we experimentally show its effectiveness in cross-lingual and low-resource scenarios. Multilingual fine-tuning with 200 samples per programming language approaches the results fine-tuned with the entire dataset on code summarization. Our experiments on three probing tasks show that adapter tuning significantly outperforms full-model fine-tuning and effectively overcomes catastrophic forgetting.

cs.SE↗
arXiv2023

ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer

Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus make these proxies more suitable for subsequent coarse-to-fine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed. Code is available at https://github.com/I2-Multimedia-Lab/ProxyFormer.

cs.CV↗
arXiv2023

A Reference Architecture for Blockchain-based Traceability Systems Using Domain-Driven Design and Microservices

Traceability systems are important for solving problems due to the increasing scale of the global supply chain, such as food safety crises and market disorder. Blockchain, as an immutable and decentralized ledger, is able to optimize the traditional traceability system by ensuring the transparency and reliability of the system data. However, the use of blockchain technology may lead to a rapid increase in the complexity of system design and development. It is challenging to address widespread and complicated business, changeable processes, and massive data in practice, which are the main factors restricting the wide application of a blockchain-based traceability system (BTS). Therefore, in this paper, we reviewed relevant studies and proposed a reference architecture for BTSs. The proposed reference architecture can improve the cohesiveness, maintainability, and extensibility of BTSs through domain-driven design (DDD) and microservices. Considering the efficiency reduction caused by massive data and complicated data structure, we further changed the traditional single blockchain framework into multiple sub-chain networks, which could improve development efficiency and system performance. With the guidance of the architecture trade-off analysis method (ATAM), we evaluated our reference architecture and implemented a prototype in the salmon supply chain scenario. The results show that our solution is effective and adaptable to meet the requirements of BTSs.

cs.SE↗
arXiv2023

Metrics for Software Process Simulation Modeling

Background: Software Process Simulation (SPS) has become an effective tool for software process management and improvement. However, its adoption in industry is less than what the research community expected due to the burden of measurement cost and the high demand for domain knowledge. The difficulty of extracting appropriate metrics with real data from process enactment is one of the great challenges. Objective: We aim to provide evidence-based support of the process metrics for software process (simulation) modeling. Method: A systematic literature review was performed by extending our previous review series to draw a comprehensive understanding of the metrics for process modeling following a meta-model of ontology of metrics in SPS. Results: We identified 145 process modeling studies that collectively involve 2130 metrics and classified them using the coding technique. Two diagrams which illustrate the high frequency causal relationships used between metrics are proposed in terms of two hierarchical levels of modeling purposes. We revisited the data issues encountered in SPS data preparing phases, as well as identified the corresponding strategies. Conclusion: The results of this study provide process modelers with an evidence-based reference of the identification and the use of metrics in SPS modeling, and further contribute to the development of the body of knowledge on software metrics in the context of process modeling. Furthermore, this study is not limited to process simulation but can be extended to software process modeling, in general. Taking simulation metrics as standards and references can further motivate and guide software developers to improve the collection, governance, and application of process data in practice.

cs.SE↗
arXiv2022

Photometric redshift estimation of galaxies in the DESI Legacy Imaging Surveys

The accurate estimation of photometric redshifts plays a crucial role in accomplishing science objectives of the large survey projects. The template-fitting and machine learning are the two main types of methods applied currently. Based on the training set obtained by cross-correlating the DESI Legacy Imaging Surveys DR9 galaxy catalogue and SDSS DR16 galaxy catalogue, the two kinds of methods are used and optimized, such as EAZY for template-fitting approach and CATBOOST for machine learning. Then the created models are tested by the cross-matched samples of the DESI Legacy Imaging SurveysDR9 galaxy catalogue with LAMOST DR7, GAMA DR3 and WiggleZ galaxy catalogues. Moreover three machine learning methods (CATBOOST, Multi-Layer Perceptron and Random Forest) are compared, CATBOOST shows its superiority for our case. By feature selection and optimization of model parameters, CATBOOST can obtain higher accuracy with optical and infrared photometric information, the best performance ($MSE=0.0032$, $σ_{NMAD}=0.0156$ and $O=0.88$ per cent) with $g \le 24.0$, $r \le 23.4$ and $z \le 22.5$ is achieved. But EAZY can provide more accurate photometric redshift estimation for high redshift galaxies, especially beyond the redhisft range of training sample. Finally, we finish the redshift estimation of all DESI DR9 galaxies with CATBOOST and EAZY, which will contribute to the further study of galaxies and their properties.

astro-ph.IM↗
arXiv2022

Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to effectively adapt pre-trained models to a new task has not been fully explored. In this paper, we propose an approach to bridge pre-trained models and code-related tasks. We exploit semantic-preserving transformation to enrich downstream data diversity, and help pre-trained models learn semantic features invariant to these semantically equivalent transformations. Further, we introduce curriculum learning to organize the transformed data in an easy-to-hard manner to fine-tune existing pre-trained models. We apply our approach to a range of pre-trained models, and they significantly outperform the state-of-the-art models on tasks for source code understanding, such as algorithm classification, code clone detection, and code search. Our experiments even show that without heavy pre-training on code data, natural language pre-trained model RoBERTa fine-tuned with our lightweight approach could outperform or rival existing code pre-trained models fine-tuned on the above tasks, such as CodeBERT and GraphCodeBERT. This finding suggests that there is still much room for improvement in code pre-trained models.

cs.SE↗
arXiv2021

Photometric Redshift Estimation of BASS DR3 Quasars by Machine Learning

Correlating BASS DR3 catalogue with ALLWISE database, the data from optical and infrared information are obtained. The quasars from SDSS are taken as training and test samples while those from LAMOST are considered as external test sample. We propose two schemes to construct the redshift estimation models with XGBoost, CatBoost and Random forest. One scheme (namely one-step model) is to predict photometric redshifts directly based on the optimal models created by these three algorithms; the other scheme (namely two-step model) is to firstly classify the data into low- and high- redshift datasets, and then predict photometric redshifts of these two datasets separately. For one-step model, the performance of these three algorithms on photometric redshift estimation is compared with different training samples, and CatBoost is superior to XGBoost and Random forest. For two-step model, the performance of these three algorithms on the classification of low- and high-redshift subsamples are compared, and CatBoost still shows the best performance. Therefore CatBoost is regard as the core algorithm of classification and regression in two-step model. By contrast with one-step model, two-step model is optimal when predicting photometric redshift of quasars, especially for high redshift quasars. Finally the two models are applied to predict photometric redshifts of all quasar candidates of BASS DR3. The number of high redshift quasar candidates is 3938 (redshift $\ge 3.5$) and 121 (redshift $\ge 4.5$) by two-step model. The predicted result will be helpful for quasar research and follow up observation of high redshift quasars.

astro-ph.IM↗
arXiv2021

deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search

With the rapid increase in the amount of public code repositories, developers maintain a great desire to retrieve precise code snippets by using natural language. Despite existing deep learning based approaches(e.g., DeepCS and MMAN) have provided the end-to-end solutions (i.e., accepts natural language as queries and shows related code fragments retrieved directly from code corpus), the accuracy of code search in the large-scale repositories is still limited by the code representation (e.g., AST) and modeling (e.g., directly fusing the features in the attention stage). In this paper, we propose a novel learnable deep Graph for Code Search (calleddeGraphCS), to transfer source code into variable-based flow graphs based on the intermediate representation technique, which can model code semantics more precisely compared to process the code as text directly or use the syntactic tree representation. Furthermore, we propose a well-designed graph optimization mechanism to refine the code representation, and apply an improved gated graph neural network to model variable-based flow graphs. To evaluate the effectiveness of deGraphCS, we collect a large-scale dataset from GitHub containing 41,152 code snippets written in C language, and reproduce several typical deep code search methods for comparison. Besides, we design a qualitative user study to verify the practical value of our approach. The experimental results have shown that deGraphCS can achieve state-of-the-art performances, and accurately retrieve code snippets satisfying the needs of the users.

cs.SE↗
arXiv2021

HFContractFuzzer: Fuzzing Hyperledger Fabric Smart Contracts for Vulnerability Detection

With its unique advantages such as decentralization and immutability, blockchain technology has been widely used in various fields in recent years. The smart contract running on the blockchain is also playing an increasingly important role in decentralized application scenarios. Therefore, the automatic detection of security vulnerabilities in smart contracts has become an urgent problem in the application of blockchain technology. Hyperledger Fabric is a smart contract platform based on enterprise-level licensed distributed ledger technology. However, the research on the vulnerability detection technology of Hyperledger Fabric smart contracts is still in its infancy. In this paper, we propose HFContractFuzzer, a method based on Fuzzing technology to detect Hyperledger Fabric smart contracts, which combines a Fuzzing tool for golang named go-fuzz and smart contracts written by golang. We use HFContractFuzzer to detect vulnerabilities in five contracts from typical sources and discover that four of them have security vulnerabilities, proving the effectiveness of the proposed method.

cs.CR↗
arXiv2021

Identification of BASS DR3 Sources as Stars, Galaxies and Quasars by XGBoost

The Beijing-Arizona Sky Survey (BASS) Data Release 3 (DR3) catalogue was released in 2019, which contains the data from all BASS and the Mosaic z-band Legacy Survey (MzLS) observations during 2015 January and 2019 March, about 200 million sources. We cross-match BASS DR3 with spectral databases from the Sloan Digital Sky Survey (SDSS) and the Large Sky Area Multi-object Fiber Spectroscopic Telescope (LAMOST) to obtain the spectroscopic classes of known samples. Then, the samples are cross-matched with ALLWISE database. Based on optical and infrared information of the samples, we use the XGBoost algorithm to construct different classifiers, including binary classification and multiclass classification. The accuracy of these classifiers with the best input pattern is larger than 90.0 per cent. Finally, all selected sources in the BASS DR3 catalogue are classified by these classifiers. The classification label and probabilities for individual sources are assigned by different classifiers. When the predicted results by binary classification are the same as multiclass classification with optical and infrared information, the number of star, galaxy and quasar candidates is separately 12 375 838 (P_S>0.95), 18 606 073 (P_G>0.95) and 798 928 (P_Q>0.95). For these sources without infrared information, the predicted results can be as a reference. Those candidates may be taken as input catalogue of LAMOST, DESI or other projects for follow up observation. The classified result will be of great help and reference for future research of the BASS DR3 sources.

astro-ph.GA↗