The capability of accurately determining code similarity is crucial in many tasks related to software development. For example, it might be essential to identify code duplicates for performing software maintenance. This research introduces a novel ensemble learning approach for code similarity assessment, combining the strengths of multiple unsupervised similarity measures. The key idea is that the strengths of a diverse set of similarity measures can complement each other and mitigate individual weaknesses, leading to improved performance. Preliminary results show that while Transformers-based CodeBERT and its variant GraphCodeBERT are undoubtedly the best option in the presence of abundant training data, in the case of specific small datasets (up to 500 samples), our ensemble achieves similar results, without prejudice to the interpretability of the resulting solution, and with a much lower associated carbon footprint due to training. The source code of this novel approach can be downloaded from //github.com/jorge-martinez-gil/ensemble-codesim.
相關內容
Software debloating tools seek to improve program security and performance by removing unnecessary code, called bloat. While many techniques have been proposed, several barriers to their adoption have emerged. Namely, debloating tools are highly specialized, making it difficult for adopters to find the right type of tool for their needs. This is further hindered by a lack of established metrics and comparative evaluations between tools. To close this information gap, we surveyed 10 years of debloating literature and several tools currently under commercial development to taxonomize knowledge about the debloating ecosystem. We then conducted a broad comparative evaluation of 10 debloating tools to determine their relative strengths and weaknesses. Our evaluation, conducted on a diverse set of 20 benchmark programs, measures tools across 12 performance, security, and correctness metrics. Our evaluation surfaces several concerning findings that contradict the prevailing narrative in the debloating literature. First, debloating tools lack the maturity required to be used on real-world software, evidenced by a slim 22% overall success rate for creating passable debloated versions of medium- and high-complexity benchmarks. Second, debloating tools struggle to produce sound and robust programs. Using our novel differential fuzzing tool, DIFFER, we discovered that only 13% of our debloating attempts produced a sound and robust debloated program. Finally, our results indicate that debloating tools typically do not improve the performance or security posture of debloated programs by a significant degree according to our evaluation metrics. We believe that our contributions in this paper will help potential adopters better understand the landscape of tools and will motivate future research and development of more capable debloating tools.
Detecting defects and vulnerabilities in the early stage has long been a challenge in software engineering. Static analysis, a technique that inspects code without execution, has emerged as a key strategy to address this challenge. Among recent advancements, the use of graph-based representations, particularly Code Property Graph (CPG), has gained traction due to its comprehensive depiction of code structure and semantics. Despite the progress, existing graph-based analysis tools still face performance and scalability issues. The main bottleneck lies in the size and complexity of CPG, which makes analyzing large codebases inefficient and memory-consuming. Also, query rules used by the current tools can be over-specific. Hence, we introduce QVoG, a graph-based static analysis platform for detecting defects and vulnerabilities. It employs a compressed CPG representation to maintain a reasonable graph size, thereby enhancing the overall query efficiency. Based on the CPG, it also offers a declarative query language to simplify the queries. Furthermore, it takes a step forward to integrate machine learning to enhance the generality of vulnerability detection. For projects consisting of 1,000,000+ lines of code, QVoG can complete analysis in approximately 15 minutes, as opposed to 19 minutes with CodeQL.
In this paper, we explore a distributed setting, where a user seeks to compute a linearly-separable Boolean function of degree $M$ from $N$ servers, each with a cache size $M$. Exploiting the fundamental concepts of sensitivity and influences of Boolean functions, we devise a novel approach to capture the interplay between dataset placement across servers and server transmissions and to determine the optimal solution for dataset placement that minimizes the communication cost. In particular, we showcase the achievability of the minimum average joint sensitivity, $\frac{N}{2^{M-1}}$, as a measure for the communication cost.
Despite extensive efforts to create fairer machine learning (ML) datasets, there remains a limited understanding of the practical aspects of dataset curation. Drawing from interviews with 30 ML dataset curators, we present a comprehensive taxonomy of the challenges and trade-offs encountered throughout the dataset curation lifecycle. Our findings underscore overarching issues within the broader fairness landscape that impact data curation. We conclude with recommendations aimed at fostering systemic changes to better facilitate fair dataset curation practices.
Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new samples (e.g., images). However, their remarkable generative performance is hindered by slow training and sampling. This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i.e., noise levels). To tackle these challenges, we present a multi-stage framework inspired by our empirical findings. These observations indicate the advantages of employing distinct parameters tailored to each timestep while retaining universal parameters shared across all time steps. Our approach involves segmenting the time interval into multiple stages where we employ custom multi-decoder U-net architecture that blends time-dependent models with a universally shared encoder. Our framework enables the efficient distribution of computational resources and mitigates inter-stage interference, which substantially improves training efficiency. Extensive numerical experiments affirm the effectiveness of our framework, showcasing significant training and sampling efficiency enhancements on three state-of-the-art diffusion models, including large-scale latent diffusion models. Furthermore, our ablation studies illustrate the impact of two important components in our framework: (i) a novel timestep clustering algorithm for stage division, and (ii) an innovative multi-decoder U-net architecture, seamlessly integrating universal and customized hyperparameters.
Exoskeleton devices impose kinematic constraints on a user's motion and affect their stability due to added mass but also due to the simplified mechanical design. This paper investigates how these constraints resulting from simplified mechanical designs impact the gait kinematics and stability of users by wearing an ankle exoskeleton with changeable degree of freedom (DoF). The exoskeleton used in this paper allows one, two, or three DoF at the ankle, simulating different levels of mechanical complexity. This effect was evaluated in a pilot study consisting of six participants walking on a straight path. The results show that increasing the exoskeleton DoF results in an improvement of several metrics, including kinematics and gait parameters. The transition from 1 DoF to 2 DoF is shown to have a larger effect than the transition from 2 DoF to 3 DoF for an ankle exoskeleton. However, an exoskeleton with 3 DoF at the ankle featured the best results. Increasing the number of DoF resulted in stability values closer the values when walking without the exoskeleton, despite the added weight of the exoskeleton.
In real-world object manipulation scenarios, multiple mobile manipulator systems may suffer from disturbances and asynchrony, leading to excessive interaction forces and causing object damage or emergency stops. This paper presents a novel distributed motion control approach aimed at reducing these unnecessary interaction forces. The control strategy only utilizes force information without the need for global position and velocity information. Disturbances are corrected through compensatory movements of the manipulators. Besides, the asymmetric, non-uniform, and time-varying communication delays between robots are also considered. The stability of the control law is rigorously proven by the Lyapunov theorem. Subsequently, the efficacy of the proposed control law is validated through simulations and experiments of collaborative object transportation by two robots. Experimental results demonstrate the effectiveness of the proposed control law in reducing interaction forces during object manipulation.
Program verification is vital for ensuring software reliability, especially in the context of increasingly complex systems. Loop invariants, remaining true before and after each iteration of loops, are crucial for this verification process. Traditional provers and machine learning based methods for generating loop invariants often require expert intervention or extensive labeled data, and typically only handle numerical property verification. These methods struggle with programs involving complex data structures and memory manipulations, limiting their applicability and automation capabilities. In this paper, we introduce a new benchmark named LIG-MM, specifically for programs with complex data structures and memory manipulations. We collect 312 programs from various sources, including daily programs from college homework, the international competition (SV-COMP), benchmarks from previous papers (SLING), and programs from real-world software systems (Linux Kernel, GlibC, LiteOS, and Zephyr). Based on LIG-MM, our findings indicate that previous methods, including GPT-4, fail to automate verification for these programs. Consequently, we propose a novel LLM-SE framework that coordinates LLM with symbolic execution, fine-tuned using self-supervised learning, to generate loop invariants. Experimental results on LIG-MM demonstrate that our LLM-SE outperforms state-of-the-art methods, offering a new direction toward automated program verification in real-world scenarios.
Formal disclosure avoidance techniques are necessary to ensure that published data can not be used to identify information about individuals. The addition of statistical noise to unpublished data can be implemented to achieve differential privacy, which provides a formal mathematical privacy guarantee. However, the infusion of noise results in data releases which are less precise than if no noise had been added, and can lead to some of the individual data points being nonsensical. Examples of this are estimates of population counts which are negative, or estimates of the ratio of counts which violate known constraints. A straightforward way to guarantee that published estimates satisfy these known constraints is to specify a statistical model and incorporate a prior on census counts and ratios which properly constrains the parameter space. We utilize rejection sampling methods for drawing samples from the posterior distribution and we show that this implementation produces estimates of population counts and ratios which maintain formal privacy, are more precise than the original unconstrained noisy measurements, and are guaranteed to satisfy prior constraints.
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191