Searcharxiv⌕ Search

arXiv subjects

Jie Hu

Publications and source records attributed to Jie Hu.

At least 181 records · Page 10Linked to original sources
arXiv2023

Augmenting Greybox Fuzzing with Generative AI

Real-world programs expecting structured inputs often has a format-parsing stage gating the deeper program space. Neither a mutation-based approach nor a generative approach can provide a solution that is effective and scalable. Large language models (LLM) pre-trained with an enormous amount of natural language corpus have proved to be effective for understanding the implicit format syntax and generating format-conforming inputs. In this paper, propose ChatFuzz, a greybox fuzzer augmented by generative AI. More specifically, we pick a seed in the fuzzer's seed pool and prompt ChatGPT generative models to variations, which are more likely to be format-conforming and thus of high quality. We conduct extensive experiments to explore the best practice for harvesting the power of generative LLM models. The experiment results show that our approach improves the edge coverage by 12.77\% over the SOTA greybox fuzzer (AFL++) on 12 target programs from three well-tested benchmarks. As for vulnerability detection, \sys is able to perform similar to or better than AFL++ for programs with explicit syntax rules but not for programs with non-trivial syntax.

cs.CR↗
arXiv2023

Graph tilings in incompatibility systems

An \emph{incompatibility system} $(G,\mathcal{F})$ consists of a graph $G$ and a family $\mathcal{F}=\{F_v\}_{v\in V(G)}$ over $G$ with $F_v\subseteq \{\{e,e'\}\in {E(G)\choose 2}: e\cap e'=\{v\}\}$. We say that two edges $e,e'\in E(G)$ are \emph{incompatible} if $\{e,e'\}\in F_v$ for some $v\in V(G)$, and otherwise \emph{compatible}. A subgraph $H$ of $G$ is \emph{compatible} if every pair of edges in $H$ are compatible. An incompatibility system $(G,\mathcal{F})$ is \emph{$Δ$-bounded} if for any vertex $v$ and any edge $e$ incident with $v$, there are at most $Δ$ members of $F_v$ containing $e$. This notion was partly motivated by a concept of transition system introduced by Kotzig in 1968, and first formulated by Krivelevich, Lee and Sudakov to study the robustness of Hamiltonicity of Dirac graphs. We prove that for any $α>0$ and any graph $H$ with $h$ vertices, there exists a constant $μ>0$ such that for any sufficiently large $n$ with $n\in h\mathbb{N}$, if $G$ is an $n$-vertex graph with $δ(G)\ge(1-\frac{1}{χ^*(H)}+α)n$ and $(G,\mathcal{F})$ is a $μn$-bounded incompatibility system, then there exists a compatible $H$-factor in $G$, where the value $χ^*(H)$ is either the chromatic number $χ(H)$ or the critical chromatic number $χ_{cr}(H)$ and we provide a dichotomy as in the Kühn--Osthus result. Moreover, we give examples $H$ for which there exists an $μn$-bounded incompatibility system $(G, \mathcal{F})$ with $n\in h\mathbb{N}$ and $δ(G)\ge(1-\frac{1}{χ^*(H)}+\fracμ{2})n$ such that $G$ contains no compatible $H$-factor. Unlike in the previous work of Kühn and Osthus on embedding $H$-factors, our proof uses the lattice-based absorption method.

math.CO↗
arXiv2023

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

Recent developments in Artificial Intelligence techniques have enabled their successful application across a spectrum of commercial and industrial settings. However, these techniques require large volumes of data to be aggregated in a centralized manner, forestalling their applicability to scenarios wherein the data is sensitive or the cost of data transmission is prohibitive. Federated Learning alleviates these problems by decentralizing model training, thereby removing the need for data transfer and aggregation. To advance the adoption of Federated Learning, more research and development needs to be conducted to address some important open questions. In this work, we propose OpenFed, an open-source software framework for end-to-end Federated Learning. OpenFed reduces the barrier to entry for both researchers and downstream users of Federated Learning by the targeted removal of existing pain points. For researchers, OpenFed provides a framework wherein new methods can be easily implemented and fairly evaluated against an extensive suite of benchmarks. For downstream users, OpenFed allows Federated Learning to be plugged and play within different subject-matter contexts, removing the need for deep expertise in Federated Learning.

cs.CR↗
arXiv2023

Polar Coded Integrated Data and Energy Networking: A Deep Neural Network Assisted End-to-End Design

Wireless sensors are everywhere. To address their energy supply, we proposed an end-to-end design for polar-coded integrated data and energy networking (IDEN), where the conventional signal processing modules, such as modulation/demodulation and channel decoding, are replaced by deep neural networks (DNNs). Moreover, the input-output relationship of an energy harvester (EH) is also modelled by a DNN. By jointly optimizing both the transmitter and the receiver as an autoencoder (AE), we minimize the bit-error-rate (BER) and maximize the harvested energy of the IDEN system, while satisfying the transmit power budget constraint determined by the normalization layer in the transmitter. Our simulation results demonstrate that the DNN aided end-to-end design conceived outperforms its conventional model-based counterpart both in terms of the harvested energy and the BER.

cs.IT↗
arXiv2023

You Only Segment Once: Towards Real-Time Panoptic Segmentation

In this paper, we propose YOSO, a real-time panoptic segmentation framework. YOSO predicts masks via dynamic convolutions between panoptic kernels and image feature maps, in which you only need to segment once for both instance and semantic segmentation tasks. To reduce the computational overhead, we design a feature pyramid aggregator for the feature map extraction, and a separable dynamic decoder for the panoptic kernel generation. The aggregator re-parameterizes interpolation-first modules in a convolution-first way, which significantly speeds up the pipeline without any additional costs. The decoder performs multi-head cross-attention via separable dynamic convolution for better efficiency and accuracy. To the best of our knowledge, YOSO is the first real-time panoptic segmentation framework that delivers competitive performance compared to state-of-the-art models. Specifically, YOSO achieves 46.4 PQ, 45.6 FPS on COCO; 52.5 PQ, 22.6 FPS on Cityscapes; 38.0 PQ, 35.4 FPS on ADE20K; and 34.1 PQ, 7.1 FPS on Mapillary Vistas. Code is available at https://github.com/hujiecpp/YOSO.

cs.CV↗
arXiv2023

DistilPose: Tokenized Pose Regression with Heatmap Distillation

In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this paper, we propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods. Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps. TDE aligns the feature spaces of heatmap-based and regression-based models by introducing tokenization, while Simulated Heatmaps transfer explicit guidance (distribution and confidence) from teacher heatmaps into student models. Extensive experiments show that the proposed DistilPose can significantly improve the performance of the regression-based models while maintaining efficiency. Specifically, on the MSCOCO validation dataset, DistilPose-S obtains 71.6% mAP with 5.36M parameter, 2.38 GFLOPs and 40.2 FPS, which saves 12.95x, 7.16x computational cost and is 4.9x faster than its teacher model with only 0.9 points performance drop. Furthermore, DistilPose-L obtains 74.4% mAP on MSCOCO validation dataset, achieving a new state-of-the-art among predominant regression-based models.

cs.CV↗
arXiv2023

Bag of Tricks with Quantized Convolutional Neural Networks for image classification

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have been proposed to reduce the memory footprint and improve inference speed. While numerous quantization methods have been proposed, they lack systematic analysis for their effectiveness. To bridge this gap, we collect and improve existing quantization methods and propose a gold guideline for post-training quantization. We evaluate the effectiveness of our proposed method with two popular models, ResNet50 and MobileNetV2, on the ImageNet dataset. By following our guidelines, no accuracy degradation occurs even after directly quantizing the model to 8-bits without additional training. A quantization-aware training based on the guidelines can further improve the accuracy in lower-bits quantization. Moreover, we have integrated a multi-stage fine-tuning strategy that works harmoniously with existing pruning techniques to reduce costs even further. Remarkably, our results reveal that a quantized MobileNetV2 with 30\% sparsity actually surpasses the performance of the equivalent full-precision model, underscoring the effectiveness and resilience of our proposed scheme.

cs.CV↗
arXiv2023

A Geometric Statistic for Quantifying Correlation Between Tree-Shaped Datasets

The magnitude of Pearson correlation between two scalar random variables can be visually judged from the two-dimensional scatter plot of an independent and identically distributed sample drawn from the joint distribution of the two variables: the closer the points lie to a straight slanting line, the greater the correlation. To the best of our knowledge, similar graphical representation or geometric quantification of tree correlation does not exist in the literature although tree-shaped datasets are frequently encountered in various fields, such as academic genealogy tree and embryonic development tree. In this paper, we introduce a geometric statistic to both represent tree correlation intuitively and quantify its magnitude precisely. The theoretical properties of the geometric statistic are provided. Large-scale simulations based on various data distributions demonstrate that the geometric statistic is precise in measuring the tree correlation. Its real application on mathematical genealogy trees also demonstrated its usefulness.

stat.ME↗
arXiv2023

Rethinking skip connection model as a learnable Markov chain

Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optimization and proven performance. Prior work has explained the effectiveness of the skip connection mechanism from different perspectives. In this work, we deep dive into the model's behaviors with skip connections which can be formulated as a learnable Markov chain. An efficient Markov chain is preferred as it always maps the input data to the target domain in a better way. However, while a model is explained as a Markov chain, it is not guaranteed to be optimized following an efficient Markov chain by existing SGD-based optimizers which are prone to get trapped in local optimal points. In order to towards a more efficient Markov chain, we propose a simple routine of penal connection to make any residual-like model become a learnable Markov chain. Aside from that, the penal connection can also be viewed as a particular model regularization and can be easily implemented with one line of code in the most popular deep learning frameworks~\footnote{Source code: \url{https://github.com/densechen/penal-connection}}. The encouraging experimental results in multi-modal translation and image recognition empirically confirm our conjecture of the learnable Markov chain view and demonstrate the superiority of the proposed penal connection.

cs.LG↗
arXiv2023

Compatible Powers of Hamilton Cycles in Dense Graphs

Motivated by the concept of transition system investigated by Kotzig in 1968, Krivelevich, Lee and Sudakov proposed a more general notion of incompatibility system to formulate the robustness of Hamiltonicity of Dirac graphs. Given a graph $G=(V,E)$, an {\em incompatibility system} $\mathcal{F}$ over $G$ is a family $\mathcal{F}=\{F_v\}_{v\in V}$ such that for every $v\in V$, $F_v$ is a family of edge pairs in $\{\{e,e'\}: e\ne e'\in E, e\cap e'=\{v\}\}$. An incompatibility system $\mathcal{F}$ is \emph{$Δ$-bounded} if for every vertex $v$ and every edge $e$ incident with $v$, there are at most $Δ$ pairs in $F_v$ containing $e$. A subgraph $H$ of $G$ is \emph{compatible} (with respect to $\mathcal{F}$) if every pair of adjacent edges $e,e'$ of $H$ satisfies $\{e,e'\} \notin F_v$, where $v=e\cap e'$. Krivelevich, Lee and Sudakov proved that there is an universal constant $μ>0$ such that for every $μn$-bounded incompatibility system $\mathcal{F}$ over a Dirac graph, there exists a compatible Hamilton cycle, which resolves a conjecture of Häggkvist from 1988. We study high powers of Hamilton cycles in this context and show that for every $γ>0$ and $k\in\mathbb{N}$, there exists a constant $μ>0$ such that for sufficiently large $n\in\mathbb{N}$ and every $μn$-bounded incompatibility system over an $n$-vertex graph $G$ with $δ(G)\ge(\frac{k}{k+1}+γ)n$, there exists a compatible $k$-th power of a Hamilton cycle in $G$. Moreover, we give a construction which has minimum degree $\frac{k}{k+1}n+Ω(n)$ and contains no compatible $k$-th power of a Hamilton cycle.

math.CO↗
arXiv2023

Elastic-Link for Binarized Neural Network

Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterparts, BNNs suffer from severe accuracy degradation. Research aiming to reduce this accuracy gap has thus far largely focused on specific network architectures with few or no 1x1 convolutional layers, for which standard binarization methods do not work well. Because 1x1 convolutions are common in the design of modern architectures (e.g. GoogleNet, ResNet, DenseNet), it is crucial to develop a method to binarize them effectively for BNNs to be more widely adopted. In this work, we propose an "Elastic-Link" (EL) module to enrich information flow within a BNN by adaptively adding real-valued input features to the subsequent convolutional output features. The proposed EL module is easily implemented and can be used in conjunction with other methods for BNNs. We demonstrate that adding EL to BNNs produces a significant improvement on the challenging large-scale ImageNet dataset. For example, we raise the top-1 accuracy of binarized ResNet26 from 57.9% to 64.0%. EL also aids convergence in the training of binarized MobileNet, for which a top-1 accuracy of 56.4% is achieved. Finally, with the integration of ReActNet, it yields a new state-of-the-art result of 71.9% top-1 accuracy.

cs.CV↗
arXiv2023

Spanning trees in graphs without large bipartite holes

We show that for any $\varepsilon>0$ and $Δ\in\mathbb{N}$, there exists $α>0$ such that for sufficiently large $n$, every $n$-vertex graph $G$ satisfying that $δ(G)\geq\varepsilon n$ and $e(X, Y)>0$ for every pair of disjoint vertex sets $X, Y\subseteq V(G)$ of size $αn$ contains all spanning trees with maximum degree at most $Δ$. This strengthens a result of Böttcher et al.

math.CO↗
arXiv2023

Orthogonal-Time-Frequency-Space Signal Design for Integrated Data and Energy Transfer: Benefits from Doppler Offsets

Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components. However, the existing work of IDET using the orthogonal-frequency-division-multiplexing (OFDM) waveforms is designed for static scenarios, which would be severely affected by the destructive Doppler offset in high-mobility scenarios. Therefore, we proposed an IDET system based on orthogonal-time-frequency-space (OTFS) waveforms with the imperfect channel assumption, which is capable of counteracting the Doppler offset in high-mobility scenarios. At the transmitter, the OTFS-IDET system superimposes the random data signals and deterministic energy signals in the delay-Doppler (DD) domain with optimally designed amplitudes. The receiver optimally splits the received signal in the power domain for achieving the best IDET performance. After formulating a non-convex optimisation problem, it is transformed into a geometric programming (GP) problem through inequality relaxations to obtain the optimal solution. The simulation demonstrates that a higher amount of energy can be harvested when employing our proposed OTFS-IDET waveforms than the conventional OFDM-IDET ones in high mobility scenarios.

eess.SP↗
arXiv2023

DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution

Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels, which significantly restricts their practical deployments on resource-limited devices. In this paper, we propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR. Specifically, we first introduce the light degradation prediction network to regress the degradation vector to simulate the real-world degradations, upon which the channel splitting vector is generated as the input for an efficient SR model. Then, a learnable octave convolution block is proposed to adaptively decide the channel splitting scale for low- and high-frequency features at each block, reducing computation overhead and memory cost by offering the large scale to low-frequency features and the small scale to the high ones. To further improve the RISR performance, Non-local regularization is employed to supplement the knowledge of patches from LR and HR subspace with free-computation inference. Extensive experiments demonstrate the effectiveness of DCS-RISR on different benchmark datasets. Our DCS-RISR not only achieves the best trade-off between computation/parameter and PSNR/SSIM metric, and also effectively handles real-world images with different degradation levels.

cs.CV↗
arXiv2022

SISO-OFDM and MISO-OFDM Counterparts for "Wideband Waveforming for Integrated Data and Energy Transfer: Creating Extra Gain Beyond Multiple Antennas and Multiple Carriers"

In this article, we proposethe SISO-OFDM and MISO-OFDM based IDET systems, which are the counterparts of our optimal wideband waveforming strategy in [1]. The fair-throughput and the sum-throughput optimisation problems are formulated. By exploiting the FP based alternating algorithm, we obtain the optimal fair-throughput and sum-throughput for both the SISO-OFDM and MISO-OFDM.

eess.SP↗
arXiv2022

Robust and Efficient Network Reconstruction in Complex System via Adaptive Signal Lasso

Network reconstruction is important to the understanding and control of collective dynamics in complex systems. Most real networks exhibit sparsely connected properties, and the connection parameter is a signal (0 or 1). Well-known shrinkage methods such as lasso or compressed sensing (CS) to recover structures of complex networks cannot suitably reveal such a property; therefore, the signal lasso method was proposed recently to solve the network reconstruction problem and was found to outperform lasso and CS methods. However, signal lasso suffers the problem that the estimated coefficients that fall between 0 and 1 cannot be successfully selected to the correct class. We propose a new method, adaptive signal lasso, to estimate the signal parameter and uncover the topology of complex networks with a small number of observations. The proposed method has three advantages: (1) It can effectively uncover the network topology with high accuracy and is capable of completely shrinking the signal parameter to either 0 or 1, which eliminates the unclassified portion in network reconstruction; (2) The method performs well in scenarios of both sparse and dense signals and is robust to noise contamination; (3) The method only needs to select one tuning parameter versus two in signal lasso, which greatly reduces the computational cost and is easy to apply. The theoretical properties of this method are studied, and numerical simulations from linear regression, evolutionary games, and Kuramoto models are explored. The method is illustrated with real-world examples from a human behavioral experiment and a world trade web.

physics.soc-ph↗
arXiv2022

Prediction of superconducting properties of materials based on machine learning models

The application of superconducting materials is becoming more and more widespread. Traditionally, the discovery of new superconducting materials relies on the experience of experts and a large number of "trial and error" experiments, which not only increases the cost of experiments but also prolongs the period of discovering new superconducting materials. In recent years, machine learning has been increasingly applied to materials science. Based on this, this manuscript proposes the use of XGBoost model to identify superconductors; the first application of deep forest model to predict the critical temperature of superconductors; the first application of deep forest to predict the band gap of materials; and application of a new sub-network model to predict the Fermi energy level of materials. Compared with our known similar literature, all the above algorithms reach state-of-the-art. Finally, this manuscript uses the above models to search the COD public dataset and identify 50 candidate superconducting materials with possible critical temperature greater than 90 K.

cond-mat.supr-con↗
arXiv2022

Nearest Neighbor Classifier with Margin Penalty for Active Learning

As deep learning becomes the mainstream in the field of natural language processing, the need for suitable active learning method are becoming unprecedented urgent. Active Learning (AL) methods based on nearest neighbor classifier are proposed and demonstrated superior results. However, existing nearest neighbor classifier are not suitable for classifying mutual exclusive classes because inter-class discrepancy cannot be assured by nearest neighbor classifiers. As a result, informative samples in the margin area can not be discovered and AL performance are damaged. To this end, we propose a novel Nearest neighbor Classifier with Margin penalty for Active Learning(NCMAL). Firstly, mandatory margin penalty are added between classes, therefore both inter-class discrepancy and intra-class compactness are both assured. Secondly, a novel sample selection strategy are proposed to discover informative samples within the margin area. To demonstrate the effectiveness of the methods, we conduct extensive experiments on for datasets with other state-of-the-art methods. The experimental results demonstrate that our method achieves better results with fewer annotated samples than all baseline methods.

cs.IR↗