arXiv subjects

Li Li

Publications and source records attributed to Li Li.

At least 397 records · Page 22Linked to original sources

arXiv2023

Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?

Recent breakthroughs in pre-trained code models, such as CodeBERT and Codex, have shown their superior performance in various downstream tasks. The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically. Recent studies reveal that even state-of-the-art pre-trained code models struggle with suggesting the correct APIs during code generation. However, the reasons for such poor API usage performance are barely investigated. To address this challenge, we propose using knowledge probing as a means of interpreting code models, which uses cloze-style tests to measure the knowledge stored in models. Our comprehensive study examines a code model's capability of understanding API fully qualified names from two different perspectives: API call and API import. Specifically, we reveal that current code models struggle with understanding API names, with pre-training strategies significantly affecting the quality of API name learning. We demonstrate that natural language context can assist code models in locating Python API names and generalize Python API name knowledge to unseen data. Our findings provide insights into the limitations and capabilities of current pre-trained code models, and suggest that incorporating API structure into the pre-training process can improve automated API usage and code representations. This work provides significance for advancing code intelligence practices and direction for future studies. All experiment results, data and source code used in this work are available at \url{https://doi.org/10.5281/zenodo.7902072}.

cs.SE↗

arXiv2023

Breaking On-device Training Memory Wall: A Systematic Survey

On-device training has become an increasingly popular approach to machine learning, enabling models to be trained directly on mobile and edge devices. However, a major challenge in this area is the limited memory available on these devices, which can severely restrict the size and complexity of the models that can be trained. In this systematic survey, we aim to explore the current state-of-the-art techniques for breaking on-device training memory walls, focusing on methods that can enable larger and more complex models to be trained on resource-constrained devices. Specifically, we first analyze the key factors that contribute to the phenomenon of memory walls encountered during on-device training. Then, we present a comprehensive literature review of on-device training, which addresses the issue of memory limitations. Finally, we summarize on-device training and highlight the open problems for future research. By providing a comprehensive overview of these techniques and their effectiveness in breaking memory walls, we hope to help researchers and practitioners in this field navigate the rapidly evolving landscape of on-device training.

cs.DC↗

arXiv2023

Towards Autonomous Cyber Operation Agents: Exploring the Red Case

Recently, reinforcement and deep reinforcement learning (RL/DRL) have been applied to develop autonomous agents for cyber network operations(CyOps), where the agents are trained in a representative environment using RL and particularly DRL algorithms. The training environment must simulate CyOps with high fidelity, which the agent aims to learn and accomplish. A good simulator is hard to achieve due to the extreme complexity of the cyber environment. The trained agent must also be generalizable to network variations because operational cyber networks change constantly. The red agent case is taken to discuss these two issues in this work. We elaborate on their essential requirements and potential solution options, illustrated by some preliminary experimentations in a Cyber Gym for Intelligent Learning (CyGIL) testbed.

cs.CR↗

arXiv2023

ReuNify: A Step Towards Whole Program Analysis for React Native Android Apps

React Native is a widely-used open-source framework that facilitates the development of cross-platform mobile apps. The framework enables JavaScript code to interact with native-side code, such as Objective-C/Swift for iOS and Java/Kotlin for Android, via a communication mechanism provided by React Native. However, previous research and tools have overlooked this mechanism, resulting in incomplete analysis of React Native app code. To address this limitation, we have developed REUNIFY, a prototype tool that integrates the JavaScript and native-side code of React Native apps into an intermediate language that can be processed by the Soot static analysis framework. By doing so, REUNIFY enables the generation of a comprehensive model of the app's behavior. Our evaluation indicates that, by leveraging REUNIFY, the Soot-based framework can improve its coverage of static analysis for the 1,007 most popular React Native Android apps, augmenting the number of lines of Jimple code by 70%. Additionally, we observed an average increase of 84% in new nodes reached in the callgraph for these apps, after integrating REUNIFY. When REUNIFY is used for taint flow analysis, an average of two additional privacy leaks were identified. Overall, our results demonstrate that REUNIFY significantly enhances the Soot-based framework's capability to analyze React Native Android apps.

cs.SE↗

arXiv2023

Bayesian reconstruction of impact parameter distributions from two observables for intermediate energy heavy ion collisions

To reconstruct the impact parameter distributions from the selected events sample or centrality, which is defined by two-observables, at intermediate energy heavy ion collisions, we extend the approach proposed by Das \textit{et al.} [Phys. Rev. C 97, 014905 (2018)], Rogly \textit{et al.} [Phys. Rev. C 98, 024902 (2018)], and Frankland \textit{et al.} [Phys. Rev. C 104, 034609 (2021)]. Based on deep investigations of the fluctuation mechanism, we found that the intrinsic fluctuations are mainly generated in the microscopic stochasticity of initialization and nucleon-nucleon collisions in the nonequilibrium process of heavy ion collisions, and this leads the observables to fluctuate with respect to impact parameter in a Gaussian form. In this work, the multiplicity of the charged particles and the total transverse momentum of the light charged particles are used simultaneously to model-independently reconstruct the impact parameter distributions for selected events or centrality based on the Bayesian method. For sorting the centrality with two observables, we propose to use the $K$-means clustering method (an unsupervised machine learning algorithm), which can automatically sort events when the class number is given. Furthermore, the reconstructed impact parameter distributions from data of the two observables can be used to learn the correlation between multiplicity and transverse momentum at different centralities, which may be useful for understanding the fragmentation mechanism.

nucl-th↗

arXiv2023

Gaussian Boson Sampling with Pseudo-Photon-Number Resolving Detectors and Quantum Computational Advantage

We report new Gaussian boson sampling experiments with pseudo-photon-number-resolving detection, which register up to 255 photon-click events. We consider partial photon distinguishability and develop a more complete model for the characterization of the noisy Gaussian boson sampling. In the quantum computational advantage regime, we use Bayesian tests and correlation function analysis to validate the samples against all current classical mockups. Estimating with the best classical algorithms to date, generating a single ideal sample from the same distribution on the supercomputer Frontier would take ~ 600 years using exact methods, whereas our quantum computer, Jiuzhang 3.0, takes only 1.27 us to produce a sample. Generating the hardest sample from the experiment using an exact algorithm would take Frontier ~ 3.1*10^10 years.

quant-ph↗

arXiv2023

CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models

Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built for proprietary or public usage, face the high risk of unauthorized exploits, resulting from data leakages, license violations, etc. Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages. Currently, watermarking methods have been proposed to prohibit inappropriate usage of image and natural language datasets. However, due to domain specificity, they are not directly applicable to code datasets, leaving the copyright protection of this emerging and important field of code data still exposed to threats. To fill this gap, we propose a method, named CodeMark, to embed user-defined imperceptible watermarks into code datasets to trace their usage in training neural code completion models. CodeMark is based on adaptive semantic-preserving transformations, which preserve the exact functionality of the code data and keep the changes covert against rule-breakers. We implement CodeMark in a toolkit and conduct an extensive evaluation of code completion models. CodeMark is validated to fulfill all desired properties of practical watermarks, including harmlessness to model accuracy, verifiability, robustness, and imperceptibility.

cs.SE↗

arXiv2023

Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning

Recent advancements in deep learning techniques have opened new possibilities for designing solutions for autonomous cyber defence. Teams of intelligent agents in computer network defence roles may reveal promising avenues to safeguard cyber and kinetic assets. In a simulated game environment, agents are evaluated on their ability to jointly mitigate attacker activity in host-based defence scenarios. Defender systems are evaluated against heuristic attackers with the goals of compromising network confidentiality, integrity, and availability. Value-based Independent Learning and Centralized Training Decentralized Execution (CTDE) cooperative Multi-Agent Reinforcement Learning (MARL) methods are compared revealing that both approaches outperform a simple multi-agent heuristic defender. This work demonstrates the ability of cooperative MARL to learn effective cyber defence tactics against varied threats.

cs.CR↗

arXiv2023

Observation of multiple steady states with engineered dissipation

Simulating the dynamics of open quantum systems is essential in achieving practical quantum computation and understanding novel nonequilibrium behaviors. However, quantum simulation of a many-body system coupled to an engineered reservoir has yet to be fully explored in present-day experiment platforms. In this work, we introduce engineered noise into a one-dimensional ten-qubit superconducting quantum processor to emulate a generic many-body open quantum system. Our approach originates from the stochastic unravellings of the master equation. By measuring the end-to-end correlation, we identify multiple steady states stemmed from a strong symmetry, which is established on the modified Hamiltonian via Floquet engineering. Furthermore, we find that the information saved in the initial state maintains in the steady state driven by the continuous dissipation on a five-qubit chain. Our work provides a manageable and hardware-efficient strategy for the open-system quantum simulation.

quant-ph↗

arXiv2023

SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning

In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide informative cues for rectification. To make the best of such rectification cues, we introduce SimFIR, a simple framework for fisheye image rectification based on self-supervised representation learning. Technically, we first split a fisheye image into multiple patches and extract their representations with a Vision Transformer (ViT). To learn fine-grained distortion representations, we then associate different image patches with their specific distortion patterns based on the fisheye model, and further subtly design an innovative unified distortion-aware pretext task for their learning. The transfer performance on the downstream rectification task is remarkably boosted, which verifies the effectiveness of the learned representations. Extensive experiments are conducted, and the quantitative and qualitative results demonstrate the superiority of our method over the state-of-the-art algorithms as well as its strong generalization ability on real-world fisheye images.

cs.CV↗

arXiv2023

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only image-level annotation, MIDN inevitably assigns high scores to some unexpected region proposals when generating pseudo labels. These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance. In this work, we explore how to ameliorate the quality of pseudo-labeling in MIDN. Formally, we devise Cyclic-Bootstrap Labeling (CBL), a novel weakly supervised object detection pipeline, which optimizes MIDN with rank information from a reliable teacher network. Specifically, we obtain this teacher network by introducing a weighted exponential moving average strategy to take advantage of various refinement modules. A novel class-specific ranking distillation algorithm is proposed to leverage the output of weighted ensembled teacher network for distilling MIDN with rank information. As a result, MIDN is guided to assign higher scores to accurate proposals among their neighboring ones, thus benefiting the subsequent pseudo labeling. Extensive experiments on the prevalent PASCAL VOC 2007 \& 2012 and COCO datasets demonstrate the superior performance of our CBL framework. Code will be available at https://github.com/Yinyf0804/WSOD-CBL/.

cs.CV↗

arXiv2023

An inverse problem for the fractionally damped wave equation

We consider an inverse problem for a Westervelt type nonlinear wave equation with fractional damping. This equation arises in nonlinear acoustic imaging, and we show the forward problem is locally well-posed. We prove that the smooth coefficient of the nonlinearity can be uniquely determined, based on the knowledge of the source-to-solution map and a priori knowledge of the coefficient in an arbitrarily small subset of the domain. Our approach relies on a second order linearization as well as the unique continuation property of the spectral fractional Laplacian.

math.AP↗

arXiv2023

HTP: Exploiting Holistic Temporal Patterns for Sequential Recommendation

Sequential recommender systems have demonstrated a huge success for next-item recommendation by explicitly exploiting the temporal order of users' historical interactions. In practice, user interactions contain more useful temporal information beyond order, as shown by some pioneering studies. In this paper, we systematically investigate various temporal information for sequential recommendation and identify three types of advantageous temporal patterns beyond order, including absolute time information, relative item time intervals and relative recommendation time intervals. We are the first to explore item-oriented absolute time patterns. While existing models consider only one or two of these three patterns, we propose a novel holistic temporal pattern based neural network, named HTP, to fully leverage all these three patterns. In particular, we introduce novel components to address the subtle correlations between relative item time intervals and relative recommendation time intervals, which render a major technical challenge. Extensive experiments on three real-world benchmark datasets show that our HTP model consistently and substantially outperforms many state-of-the-art models. Our code is publically available at https://github.com/623851394/HTP/tree/main/HTP-main

cs.IR↗

arXiv2023

IR Design for Application-Specific Natural Language: A Case Study on Traffic Data

In the realm of software applications in the transportation industry, Domain-Specific Languages (DSLs) have enjoyed widespread adoption due to their ease of use and various other benefits. With the ceaseless progress in computer performance and the rapid development of large-scale models, the possibility of programming using natural language in specified applications - referred to as Application-Specific Natural Language (ASNL) - has emerged. ASNL exhibits greater flexibility and freedom, which, in turn, leads to an increase in computational complexity for parsing and a decrease in processing performance. To tackle this issue, our paper advances a design for an intermediate representation (IR) that caters to ASNL and can uniformly process transportation data into graph data format, improving data processing performance. Experimental comparisons reveal that in standard data query operations, our proposed IR design can achieve a speed improvement of over forty times compared to direct usage of standard XML format data.

cs.SE↗

arXiv2023

Offline and Online Optical Flow Enhancement for Deep Video Compression

Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the existing deep video compression networks. Indeed, these networks often adopt pre-trained optical flow estimation networks for motion estimation. The optical flows, however, may be less suitable for video compression due to the following two factors. First, the optical flow estimation networks were trained to perform inter-frame prediction as accurately as possible, but the optical flows themselves may cost too many bits to encode. Second, the optical flow estimation networks were trained on synthetic data, and may not generalize well enough to real-world videos. We address the twofold limitations by enhancing the optical flows in two stages: offline and online. In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e.g. H.266/VVC, as we believe the motion information of H.266/VVC achieves a better rate-distortion trade-off. In the online stage, we further optimize the latent features of the optical flows with a gradient descent-based algorithm for the video to be compressed, so as to enhance the adaptivity of the optical flows. We conduct experiments on a state-of-the-art deep video compression scheme, DCVC. Experimental results demonstrate that the proposed offline and online enhancement together achieves on average 12.8% bitrate saving on the tested videos, without increasing the model or computational complexity of the decoder side.

cs.CV↗

arXiv2023

Static de-Sitter Black Holes Abhor Charged Scalar Hair

We prove a no charged scalar hair theorem for static black holes in de-Sitter spacetime in the region between the event horizon and the cosmological horizon. The proof does not depend on the assumption of spherical symmetry. It allows for general non-minimal coupling functions of the scalar field to gravity and electromagnetic fields, and for higher curvature term corrections to Einstein gravity. The extension to other asympitotic spacetimes is applicable by requiring appropriate boundary conditions. Our result excludes the possibility for spontaneous scalarization of charged scalar around static charged de-Sitter black holes.

gr-qc↗

arXiv2023

Nakajima's quiver varieties and triangular bases of rank-2 cluster algebras

Berenstein and Zelevinsky introduced quantum cluster algebras [Adv. Math, 2005] and the triangular bases [IMRN, 2014]. The support conjecture by Lee-Li-Rupel-Zelevinsky [PNAS, 2014] asserts that the support of a triangular basis element for a rank-2 cluster algebra is bounded by an explicitly described region that is possibly concave. In this paper, we prove the support conjecture for all skew-symmetric rank-2 cluster algebras.

math.AG↗

arXiv2023

Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system

Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR). In this work, we propose a phonetic-assisted multi target units (PMU) modeling approach, to enhance the Conformer-Transducer ASR system in a progressive representation learning manner. Specifically, PMU first uses the pronunciation-assisted subword modeling (PASM) and byte pair encoding (BPE) to produce phonetic-induced and text-induced target units separately; Then, three new frameworks are investigated to enhance the acoustic encoder, including a basic PMU, a paraCTC and a pcaCTC, they integrate the PASM and BPE units at different levels for CTC and transducer multi-task training. Experiments on both LibriSpeech and accented ASR tasks show that, the proposed PMU significantly outperforms the conventional BPE, it reduces the WER of LibriSpeech clean, other, and six accented ASR testsets by relative 12.7%, 6.0% and 7.7%, respectively.

eess.AS↗