arXiv subjects

Hai Jin

Publications and source records attributed to Hai Jin.

At least 91 records · Page 5Linked to original sources

arXiv2021

Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations

User interest exploration is an important and challenging topic in recommender systems, which alleviates the closed-loop effects between recommendation models and user-item interactions. Contextual bandit (CB) algorithms strive to make a good trade-off between exploration and exploitation so that users' potential interests have chances to expose. However, classical CB algorithms can only be applied to a small, sampled item set (usually hundreds), which forces the typical applications in recommender systems limited to candidate post-ranking, homepage top item ranking, ad creative selection, or online model selection (A/B test). In this paper, we introduce two simple but effective hierarchical CB algorithms to make a classical CB model (such as LinUCB and Thompson Sampling) capable to explore users' interest in the entire item space without limiting it to a small item set. We first construct a hierarchy item tree via a bottom-up clustering algorithm to organize items in a coarse-to-fine manner. Then we propose a hierarchical CB (HCB) algorithm to explore users' interest in the hierarchy tree. HCB takes the exploration problem as a series of decision-making processes, where the goal is to find a path from the root to a leaf node, and the feedback will be back-propagated to all the nodes in the path. We further propose a progressive hierarchical CB (pHCB) algorithm, which progressively extends visible nodes which reach a confidence level for exploration, to avoid misleading actions on upper-level nodes in the sequential decision-making process. Extensive experiments on two public recommendation datasets demonstrate the effectiveness and flexibility of our methods.

cs.IR↗

arXiv2021

ScalaBFS: A Scalable BFS Accelerator on HBM-Enhanced FPGAs

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalaBFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalaBFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalaBFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalaBFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalaBFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280).

cs.AR↗

arXiv2021

Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data

Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, due to the heterogeneity of the system and data, many approaches suffer from the "client-drift" issue that could significantly slow down the convergence of the global model training. As clients perform local updates on heterogeneous data through heterogeneous systems, their local models drift apart. To tackle this issue, one intuitive idea is to guide the local model training by the global teachers, i.e., past global models, where each client learns the global knowledge from past global models via adaptive knowledge distillation techniques. Coming from these insights, we propose a novel approach for heterogeneous federated learning, namely FedGKD, which fuses the knowledge from historical global models for local training to alleviate the "client-drift" issue. In this paper, we evaluate FedGKD with extensive experiments on various CV/NLP datasets (i.e., CIFAR-10/100, Tiny-ImageNet, AG News, SST5) and different heterogeneous settings. The proposed method is guaranteed to converge under common assumptions, and achieves superior empirical accuracy in fewer communication runs than five state-of-the-art methods.

cs.LG↗

arXiv2021

Towards Making Deep Learning-based Vulnerability Detectors Robust

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention. In particular, deep learning-based vulnerability detectors, or DL-based detectors, are attractive because they do not need human experts to define features or patterns of vulnerabilities. However, such detectors' robustness is unclear. In this paper, we initiate the study in this aspect by demonstrating that DL-based detectors are not robust against simple code transformations, dubbed attacks in this paper, as these transformations may be leveraged for malicious purposes. As a first step towards making DL-based detectors robust against such attacks, we propose an innovative framework, dubbed ZigZag, which is centered at (i) decoupling feature learning and classifier learning and (ii) using a ZigZag-style strategy to iteratively refine them until they converge to robust features and robust classifiers. Experimental results show that the ZigZag framework can substantially improve the robustness of DL-based detectors.

cs.CR↗

arXiv2021

Significant Inverse Magnetocaloric Effect induced by Quantum Criticality

The criticality-enhanced magnetocaloric effect (MCE) near a field-induced quantum critical point (QCP) in the spin systems constitutes a very promising and highly tunable alternative to conventional adiabatic demagnetization refrigeration. Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP. In this work, through efficient and accurate many-body calculations, we show there exists a significant inverse MCE(iMCE) in the spin-1 quantum chain materials(CH$_3$)$_4$NNi(NO$_2$)$_3$ (TMNIN) and NiCl$_2$-4SC(NH$_2$)$_2$ (DTN), where DTN has substantial low-$T$ refrigeration capacity while requiring only moderate magnetic fields. The iMCE characteristics, including the adiabatic temperature change $ΔT_{\rm ad}$, isothermal entropy change $ΔS$, differential Grüneisen parameter, and the entropy change rate, are obtained with quantum many-body calculations at finite temperature. The cooling performance, i.e., the efficiency factor and hold time, of the two compounds is also discussed. Based on the many-body calculations on realistic models for the spin-chain materials, we conclude that the compound DTN constitutes a very promising and highly efficient quantum magnetic coolant with pronounced iMCE properties. We advocate that such quantum magnets can be used in cryofree refrigeration for space applications and quantum computing environments.

cond-mat.str-el↗

arXiv2021

HomDroid: Detecting Android Covert Malware by Social-Network Homophily Analysis

Android has become the most popular mobile operating system. Correspondingly, an increasing number of Android malware has been developed and spread to steal users' private information. There exists one type of malware whose benign behaviors are developed to camouflage malicious behaviors. The malicious component occupies a small part of the entire code of the application (app for short), and the malicious part is strongly coupled with the benign part. In this case, the malware may cause false negatives when malware detectors extract features from the entire apps to conduct classification because the malicious features of these apps may be hidden among benign features. Moreover, some previous work aims to divide the entire app into several parts to discover the malicious part. However, the premise of these methods to commence app partition is that the connections between the normal part and the malicious part are weak. In this paper, we call this type of malware as Android covert malware and generate the first dataset of covert malware. To detect them, we first conduct static analysis to extract the call graphs. Through the deep analysis on graphs, we observe that although the correlations between the normal part and the malicious part in these graphs are high, the degree of these correlations has a distribution. Based on the observation, we design HomDroid to detect covert malware by analyzing the homophily of call graphs. We identify the ideal threshold of correlation to distinguish the normal part and the malicious part based on the evaluation results on a dataset of 4,840 benign apps and 3,385 covert malicious apps. According to our evaluation results, HomDroid is capable of detecting 96.8% of covert malware while the False Negative Rates of another four state-of-the-art systems (i.e., PerDroid, Drebin, MaMaDroid, and IntDroid) are 30.7%, 16.3%, 15.2%, and 10.4%, respectively.

cs.CR↗

arXiv2021

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment. Most existing research addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three elements and has the problem of error propagation. In this paper, we propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model (S3E2) to fully exploit the syntactic and semantic relationships between the triplet elements and jointly extract them. Specifically, we design a Graph-Sequence duel representation and modeling paradigm for the task of ASTE: we represent the semantic and syntactic relationships between word pairs in a sentence by graph and encode it by Graph Neural Networks (GNNs), as well as modeling the original sentence by LSTM to preserve the sequential information. Under this setting, we further apply a more efficient inference strategy for the extraction of triplets. Extensive evaluations on four benchmark datasets show that S3E2 significantly outperforms existing approaches, which proves our S3E2's superiority and flexibility in an end-to-end fashion.

cs.CL↗

arXiv2021

VulDeeLocator: A Deep Learning-based Fine-grained Vulnerability Detector

Automatically detecting software vulnerabilities is an important problem that has attracted much attention from the academic research community. However, existing vulnerability detectors still cannot achieve the vulnerability detection capability and the locating precision that would warrant their adoption for real-world use. In this paper, we present a vulnerability detector that can simultaneously achieve a high detection capability and a high locating precision, dubbed Vulnerability Deep learning-based Locator (VulDeeLocator). In the course of designing VulDeeLocator, we encounter difficulties including how to accommodate semantic relations between the definitions of types as well as macros and their uses across files, how to accommodate accurate control flows and variable define-use relations, and how to achieve high locating precision. We solve these difficulties by using two innovative ideas: (i) leveraging intermediate code to accommodate extra semantic information, and (ii) using the notion of granularity refinement to pin down locations of vulnerabilities. When applied to 200 files randomly selected from three real-world software products, VulDeeLocator detects 18 confirmed vulnerabilities (i.e., true-positives). Among them, 16 vulnerabilities correspond to known vulnerabilities; the other two are not reported in the National Vulnerability Database (NVD) but have been "silently" patched by the vendor of Libav when releasing newer versions.

cs.CR↗

arXiv2021

Sparse online relative similarity learning

For many data mining and machine learning tasks, the quality of a similarity measure is the key for their performance. To automatically find a good similarity measure from datasets, metric learning and similarity learning are proposed and studied extensively. Metric learning will learn a Mahalanobis distance based on positive semi-definite (PSD) matrix, to measure the distances between objectives, while similarity learning aims to directly learn a similarity function without PSD constraint so that it is more attractive. Most of the existing similarity learning algorithms are online similarity learning method, since online learning is more scalable than offline learning. However, most existing online similarity learning algorithms learn a full matrix with d 2 parameters, where d is the dimension of the instances. This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity. To solve this issue, we introduce several Sparse Online Relative Similarity (SORS) learning algorithms, which learn a sparse model during the learning process, so that the memory and computational cost can be significantly reduced. We theoretically analyze the proposed algorithms, and evaluate them on some real-world high dimensional datasets. Encouraging empirical results demonstrate the advantages of our approach in terms of efficiency and efficacy.

cs.LG↗

arXiv2021

Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder

In the real world, networks often contain multiple relationships among nodes, manifested as the heterogeneity of the edges in the networks. We convert the heterogeneous networks into multiple views by using each view to describe a specific type of relationship between nodes, so that we can leverage the collaboration of multiple views to learn the representation of networks with heterogeneous edges. Given this, we propose a \emph{regularized graph auto-encoders} (RGAE) model, committed to utilizing abundant information in multiple views to learn robust network representations. More specifically, RGAE designs shared and private graph auto-encoders as main components to capture high-order nonlinear structure information of the networks. Besides, two loss functions serve as regularization to extract consistent and unique information, respectively. Concrete experimental results on realistic datasets indicate that our model outperforms state-of-the-art baselines in practical applications.

cs.SI↗

arXiv2021

Multi-Task Representation Learning with Multi-View Graph Convolutional Networks

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multi-task multi-view learning in this paper. We first explain the feasibility and advantages of multi-task multi-view learning for these two tasks. Then we propose a novel model named as MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multi-view graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network datasets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks.

cs.SI↗

arXiv2021

SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities

The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it alleviates the requirement to manually define features. Despite the tremendous success of deep learning in other application domains, its applicability to vulnerability detection is not systematically understood. In order to fill this void, we propose the first systematic framework for using deep learning to detect vulnerabilities in C/C++ programs with source code. The framework, dubbed Syntax-based, Semantics-based, and Vector Representations (SySeVR), focuses on obtaining program representations that can accommodate syntax and semantic information pertinent to vulnerabilities. Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database. Among these 15 vulnerabilities, 7 are unknown and have been reported to the vendors, and the other 8 have been "silently" patched by the vendors when releasing newer versions of the pertinent software products.

cs.LG↗

arXiv2020

NaturalCC: A Toolkit to Naturalize the Source Code Corpus

We present NaturalCC, an efficient and extensible toolkit to bridge the gap between natural language and programming language, and facilitate the research on big code analysis. Using NaturalCC, researchers both from natural language or programming language communities can quickly and easily reproduce the state-of-the-art baselines and implement their approach. NaturalCC is built upon Fairseq and PyTorch, providing (1) an efficient computation with multi-GPU and mixed-precision data processing for fast model training, (2) a modular and extensible framework that makes it easy to reproduce or implement an approach for big code analysis, and (3) a command line interface and a graphical user interface to demonstrate each model's performance. Currently, we have included several state-of-the-art baselines across different tasks (e.g., code completion, code comment generation, and code retrieval) for demonstration. The video of this demo is available at https://www.youtube.com/watch?v=q4W5VSI-u3E&t=25s.

cs.SE↗

arXiv2020

Optimizing Memory Performance of Xilinx FPGAs under Vitis

Plenty of research efforts have been devoted to FPGA-based acceleration, due to its low latency and high energy efficiency. However, using the original low-level hardware description languages like Verilog to program FPGAs requires generally good knowledge of hardware design details and hand-on experiences. Fortunately, the FPGA community intends to address this low programmability issues. For example, , with the intention that programming FPGAs is just as easy as programming GPUs. Even though Vitis is proven to increase programmability, we cannot directly obtain high performance without careful design regarding hardware pipeline and memory subsystem.In this paper, we focus on the memory subsystem, comprehensively and systematically benchmarking the effect of optimization methods on memory performance. Upon benchmarking, we quantitatively analyze the typical memory access patterns for a broad range of applications, including AI, HPC, and database. Further, we also provide the corresponding optimization direction for each memory access pattern so as to improve overall performance.

cs.DC↗

arXiv2020

A Survey of Non-Volatile Main Memory Technologies: State-of-the-Arts, Practices, and Future Directions

Non-Volatile Main Memories (NVMMs) have recently emerged as promising technologies for future memory systems. Generally, NVMMs have many desirable properties such as high density, byte-addressability, non-volatility, low cost, and energy efficiency, at the expense of high write latency, high write power consumption and limited write endurance. NVMMs have become a competitive alternative of Dynamic Random Access Memory (DRAM), and will fundamentally change the landscape of memory systems. They bring many research opportunities as well as challenges on system architectural designs, memory management in operating systems (OSes), and programming models for hybrid memory systems. In this article, we first revisit the landscape of emerging NVMM technologies, and then survey the state-of-the-art studies of NVMM technologies. We classify those studies with a taxonomy according to different dimensions such as memory architectures, data persistence, performance improvement, energy saving, and wear leveling. Second, to demonstrate the best practices in building NVMM systems, we introduce our recent work of hybrid memory system designs from the dimensions of architectures, systems, and applications. At last, we present our vision of future research directions of NVMMs and shed some light on design challenges and opportunities.

cs.DC↗

arXiv2020

$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection

Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to pinpoint the type of a vulnerability in question. Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i.e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i.e., incapable of addressing multiclass classification). In this paper, we propose the first deep learning-based system for multiclass vulnerability detection, dubbed $μ$VulDeePecker. The key insight underlying $μ$VulDeePecker is the concept of code attention, which can capture information that can help pinpoint types of vulnerabilities, even when the samples are small. For this purpose, we create a dataset from scratch and use it to evaluate the effectiveness of $μ$VulDeePecker. Experimental results show that $μ$VulDeePecker is effective for multiclass vulnerability detection and that accommodating control-dependence (other than data-dependence) can lead to higher detection capabilities.

cs.CR↗

arXiv2019

A Survey on Graph Processing Accelerators: Challenges and Opportunities

Graph is a well known data structure to represent the associated relationships in a variety of applications, e.g., data science and machine learning. Despite a wealth of existing efforts on developing graph processing systems for improving the performance and/or energy efficiency on traditional architectures, dedicated hardware solutions, also referred to as graph processing accelerators, are essential and emerging to provide the benefits significantly beyond those pure software solutions can offer. In this paper, we conduct a systematical survey regarding the design and implementation of graph processing accelerator. Specifically, we review the relevant techniques in three core components toward a graph processing accelerator: preprocessing, parallel graph computation and runtime scheduling. We also examine the benchmarks and results in existing studies for evaluating a graph processing accelerator. Interestingly, we find that there is not an absolute winner for all three aspects in graph acceleration due to the diverse characteristics of graph processing and complexity of hardware configurations. We finially present to discuss several challenges in details, and to further explore the opportunities for the future research.

cs.DC↗

arXiv2019

Optimizing the SSD Burst Buffer by Traffic Detection

Currently, Burst buffer has been proposed to manage the SSD buffering of bursty write requests. Although burst buffer can improve I/O performance in many cases, we find that it has some limitations such as requiring large SSD capacity and harmonious overlapping between computation phase and data flushing phase. In this paper, we propose a scheme, called SSDUP+1. SSDUP+ aims to improve the burst buffer by addressing the above limitations. First, in order to reduce the demand for the SSD capacity, we develop a novel method to detect and quantify the data randomness in the write traffic. Further, an adaptive algorithm is proposed to classify the random writes dynamically. By doing so, much less SSD capacity is required to achieve the similar performance as other burst buffer schemes. Next, in order to overcome the difficulty of perfectly overlapping the computation phase and the flushing phase, we propose a pipeline mechanism for the SSD buffer, in which data buffering and flushing are performed in pipeline. In addition, in order to improve the I/O throughput, we adopt a traffic-aware flushing strategy to reduce the I/O interference in HDD. Finally, in order to further improve the performance of buffering random writes in SSD, SSDUP+ transforms the random writes to sequential writes in SSD by storing the data with a log structure. Further, SSDUP+ uses the AVL tree structure to store the sequence information of the data. We have implemented a prototype of SSDUP+ based on OrangeFS and conducted extensive experiments. The experimental results show that our proposed SSDUP+ can save an average of 50% SSD space, while delivering almost the same performance as other common burst buffer schemes. In addition, SSDUP+ can save about 20% SSD space compared with the previous version of this work, SSDUP, while achieving 20%-30% higher I/O throughput than SSDUP.

cs.DC↗