arXiv subjects

Chao Wang

Publications and source records attributed to Chao Wang.

At least 433 records · Page 24Linked to original sources

arXiv2023

Systematic Testing of the Data-Poisoning Robustness of KNN

Data poisoning aims to compromise a machine learning based software component by contaminating its training set to change its prediction results for test inputs. Existing methods for deciding data-poisoning robustness have either poor accuracy or long running time and, more importantly, they can only certify some of the truly-robust cases, but remain inconclusive when certification fails. In other words, they cannot falsify the truly-non-robust cases. To overcome this limitation, we propose a systematic testing based method, which can falsify as well as certify data-poisoning robustness for a widely used supervised-learning technique named k-nearest neighbors (KNN). Our method is faster and more accurate than the baseline enumeration method, due to a novel over-approximate analysis in the abstract domain, to quickly narrow down the search space, and systematic testing in the concrete domain, to find the actual violations. We have evaluated our method on a set of supervised-learning datasets. Our results show that the method significantly outperforms state-of-the-art techniques, and can decide data-poisoning robustness of KNN prediction results for most of the test inputs.

cs.SE↗

arXiv2023

Satellite Computing: A Case Study of Cloud-Native Satellites

The on-orbit processing of massive satellite-native data relies on powerful computing power. Satellite computing has started to gain attention, with researchers proposing various algorithms, applications, and simulation testbeds. Unfortunately, a practical platform for deploying satellite computing is currently lacking. As a result, the industry needs to make relentless efforts to achieve this goal. We suggest using cloud-native technology to enhance the computing power of LEO satellites. The first main satellite of the Tiansuan constellation, BUPT-1, is a significant example of a cloud-native satellite. Prior to delving into the details of BUPT-1, we define the essential concepts of cloud-native satellites, i.e., the cloud-native load and cloud-native platform. Afterwards, we present the design scheme of cloud-native satellites, including the architecture of BUPT-1 and the experimental subjects it can support. Two validation tests are shown to reflect the operation and capability of BUPT-1. Besides, we predict possible research fields that could shape the future of satellites in the next decade.

cs.DC↗

arXiv2023

Certifying the Fairness of KNN in the Presence of Dataset Bias

We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, the k-nearest neighbors (KNN), under the assumption that the training data may have historical bias caused by systematic mislabeling of samples from a protected minority group. To the best of our knowledge, this is the first certification method for KNN based on three variants of the fairness definition: individual fairness, $ε$-fairness, and label-flipping fairness. We first define the fairness certification problem for KNN and then propose sound approximations of the complex arithmetic computations used in the state-of-the-art KNN algorithm. This is meant to lift the computation results from the concrete domain to an abstract domain, to reduce the computational cost. We show effectiveness of this abstract interpretation based technique through experimental evaluation on six datasets widely used in the fairness research literature. We also show that the method is accurate enough to obtain fairness certifications for a large number of test inputs, despite the presence of historical bias in the datasets.

cs.LG↗

arXiv2023

The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these factors has been overlooked in previous research. To address this gap, we propose a new weakly supervised learning framework for knowledge distillation in video classification that is designed to improve the efficiency and accuracy of the student model. Our approach leverages the concept of substage-based learning to distill knowledge based on the combination of student substages and the correlation of corresponding substages. We also employ the progressive cascade training method to address the accuracy loss caused by the large capacity gap between the teacher and the student. Additionally, we propose a pseudo-label optimization strategy to improve the initial data label. To optimize the loss functions of different distillation substages during the training process, we introduce a new loss method based on feature distribution. We conduct extensive experiments on both real and simulated data sets, demonstrating that our proposed approach outperforms existing distillation methods in terms of knowledge distillation for video classification tasks. Our proposed substage-based distillation approach has the potential to inform future research on label-efficient learning for video data.

cs.CV↗

arXiv2023

Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review

Bayesian inference has many advantages in robotic motion planning over four perspectives: The uncertainty quantification of the policy, safety (risk-aware) and optimum guarantees of robot motions, data-efficiency in training of reinforcement learning, and reducing the sim2real gap when the robot is applied to real-world tasks. However, the application of Bayesian inference in robotic motion planning is lagging behind the comprehensive theory of Bayesian inference. Further, there are no comprehensive reviews to summarize the progress of Bayesian inference to give researchers a systematic understanding in robotic motion planning. This paper first provides the probabilistic theories of Bayesian inference which are the preliminary of Bayesian inference for complex cases. Second, the Bayesian estimation is given to estimate the posterior of policies or unknown functions which are used to compute the policy. Third, the classical model-based Bayesian RL and model-free Bayesian RL algorithms for robotic motion planning are summarized, while these algorithms in complex cases are also analyzed. Fourth, the analysis of Bayesian inference in inverse RL is given to infer the reward functions in a data-efficient manner. Fifth, we systematically present the hybridization of Bayesian inference and RL which is a promising direction to improve the convergence of RL for better motion planning. Sixth, given the Bayesian inference, we present the interpretable and safe robotic motion plannings which are the hot research topic recently. Finally, all algorithms reviewed in this paper are summarized analytically as the knowledge graphs, and the future of Bayesian inference for robotic motion planning is also discussed, to pave the way for data-efficient, explainable, and safe robotic motion planning strategies for practical applications.

cs.AI↗

arXiv2023

One-step Preparation of ZnO Electron Transport Layers Functionalized with Benzoic Acid Derivatives

We present a "one-step" approach to modify ZnO electron transport layers (ETLs) used in organic solar cells. This approach involves adding benzoic acid (BZA) derivatives directly to the ZnO precursor solution, which are then present at the surface of the resulting ZnO film. We demonstrate this approach for three different BZA derivatives, namely benzoic acid, chlorobenzoic acid, and 4-hydrazinobenzoic acid. For all molecules, improved device performance and stability is demonstrated in solar cells using an active layer blend of PTQ10 (donor) and ITIC-Br (non-fullerene acceptor) compared to such cells prepared using untreated ZnO. Furthermore, similar or improved device performance and stability is demonstrated compared to conventional PEIE treatment of ZnO. The presence of the BZA derivatives at the surface after processing is established using X-ray photoelectron spectroscopy and near-edge X-ray absorption fine-structure spectroscopy. From atomic force microscopy analysis and X-ray diffraction studies, the addition of BZA derivatives appears to restrict ZnO grain growth; however, this does not negatively impact device performance. ZnO layers treated with BZA derivatives also exhibit higher water contact angle and lower work function compared to untreated ZnO. This approach enables simplification of device manufacture while still allowing optimization of the surface properties of metal oxide ETLs. Keywords: electron transport layers, zinc oxide, organic solar cells, surface modification

cond-mat.mtrl-sci↗

arXiv2023

Generalized Time Warping Invariant Dictionary Learning for Time Series Classification and Clustering

Dictionary learning is an effective tool for pattern recognition and classification of time series data. Among various dictionary learning techniques, the dynamic time warping (DTW) is commonly used for dealing with temporal delays, scaling, transformation, and many other kinds of temporal misalignments issues. However, the DTW suffers overfitting or information loss due to its discrete nature in aligning time series data. To address this issue, we propose a generalized time warping invariant dictionary learning algorithm in this paper. Our approach features a generalized time warping operator, which consists of linear combinations of continuous basis functions for facilitating continuous temporal warping. The integration of the proposed operator and the dictionary learning is formulated as an optimization problem, where the block coordinate descent method is employed to jointly optimize warping paths, dictionaries, and sparseness coefficients. The optimized results are then used as hyperspace distance measures to feed classification and clustering algorithms. The superiority of the proposed method in terms of dictionary learning, classification, and clustering is validated through ten sets of public datasets in comparing with various benchmark methods.

stat.ML↗

arXiv2023

Classical-Assisted Quantum Ground State Preparation with Tensor Network States and Monte Carlo Sampling

Quantum computing offers potential solutions for finding ground states in condensed-matter physics and chemistry. However, achieving effective ground state preparation is also computationally hard for arbitrary Hamiltonians. It is necessary to propose certain assumptions to make this problem efficiently solvable, including preparing a trial state of a non-trivial overlap with the genuine ground state. Here, we propose a classical-assisted quantum ground state preparation method for quantum many-body systems, combining Tensor Network States (TNS) and Monte Carlo (MC) sampling as a heuristic method to prepare a trial state with a non-trivial overlap with the genuine ground state. We extract a sparse trial state by sampling from TNS, which can be efficiently prepared by a quantum algorithm on early fault-tolerant quantum computers. Our method demonstrates a polynomial improvement in scaling of overlap between the trial state and genuine ground state compared to random trial states, as evidenced by numerical tests on the spin-$1/2$ $J_1$-$J_2$ Heisenberg model. Furthermore, our method is a novel approach to hybridize a classical numerical method and a quantum algorithm and brings inspiration to ground state preparation in other fields.

quant-ph↗

arXiv2023

SoK: Decoding the Super App Enigma: The Security Mechanisms, Threats, and Trade-offs in OS-alike Apps

The super app paradigm, exemplified by platforms such as WeChat and AliPay, has revolutionized the mobile app landscape by enabling third-party developers to deploy add-ons within these apps. These add-ons, known as miniapps, leverage user data hosted by the super app platforms to provide a wide range of services, such as shopping and gaming. With the rise of miniapps, super apps have transformed into "operating systems", offering encapsulated APIs to miniapp developers as well as in-app miniapp stores for users to explore and download miniapps. In this paper, we provide the first systematic study to consolidate the current state of knowledge in this field from the security perspective: the security measures, threats, and trade-offs of this paradigm. Specifically, we summarize 13 security mechanisms and 10 security threats in super app platforms, followed by a root cause analysis revealing that the security assumptions still may be violated due to issues in underlying systems, implementation of isolation, and vetting. Additionally, we also systematize open problems and trade-offs that need to be addressed by future works to help enhance the security and privacy of this new paradigm.

cs.CR↗

arXiv2023

Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections

Sparse data are common. The traditional ``handcrafted'' features are often sparse. Embedding vectors from trained models can also be very sparse, for example, embeddings trained via the ``ReLu'' activation function. In this paper, we report our exploration of efficient search in sparse data with graph-based ANN algorithms (e.g., HNSW, or SONG which is the GPU version of HNSW), which are popular in industrial practice, e.g., search and ads (advertising). We experiment with the proprietary ads targeting application, as well as benchmark public datasets. For ads targeting, we train embeddings with the standard ``cosine two-tower'' model and we also develop the ``chi-square two-tower'' model. Both models produce (highly) sparse embeddings when they are integrated with the ``ReLu'' activation function. In EBR (embedding-based retrieval) applications, after we the embeddings are trained, the next crucial task is the approximate near neighbor (ANN) search for serving. While there are many ANN algorithms we can choose from, in this study, we focus on the graph-based ANN algorithm (e.g., HNSW-type). Sparse embeddings should help improve the efficiency of EBR. One benefit is the reduced memory cost for the embeddings. The other obvious benefit is the reduced computational time for evaluating similarities, because, for graph-based ANN algorithms such as HNSW, computing similarities is often the dominating cost. In addition to the effort on leveraging data sparsity for storage and computation, we also integrate ``sign cauchy random projections'' (SignCRP) to hash vectors to bits, to further reduce the memory cost and speed up the ANN search. In NIPS'13, SignCRP was proposed to hash the chi-square similarity, which is a well-adopted nonlinear kernel in NLP and computer vision. Therefore, the chi-square two-tower model, SignCRP, and HNSW are now tightly integrated.

cs.IR↗

arXiv2023

Uncovering and Exploiting Hidden APIs in Mobile Super Apps

Mobile applications, particularly those from social media platforms such as WeChat and TikTok, are evolving into "super apps" that offer a wide range of services such as instant messaging and media sharing, e-commerce, e-learning, and e-government. These super apps often provide APIs for developers to create "miniapps" that run within the super app. These APIs should have been thoroughly scrutinized for security. Unfortunately, we find that many of them are undocumented and unsecured, potentially allowing miniapps to bypass restrictions and gain higher privileged access. To systematically identify these hidden APIs before they are exploited by attackers, we developed a tool APIScope with both static analysis and dynamic analysis, where static analysis is used to recognize hidden undocumented APIs, and dynamic analysis is used to confirm whether the identified APIs can be invoked by an unprivileged 3rdparty miniapps. We have applied APIScope to five popular super apps (i.e., WeChat, WeCom, Baidu, QQ, and Tiktok) and found that all of them contain hidden APIs, many of which can be exploited due to missing security checks. We have also quantified the hidden APIs that may have security implications by verifying if they have access to resources protected by Android permissions. Furthermore, we demonstrate the potential security hazards by presenting various attack scenarios, including unauthorized access to any web pages, downloading and installing malicious software, and stealing sensitive information. We have reported our findings to the relevant vendors, some of whom have patched the vulnerabilities and rewarded us with bug bounties.

cs.CR↗

arXiv2023

Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment

Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually tailored for one or two specific tasks, but fail to conquer a wide range of speech-text tasks. In addition, existing speech-text pre-training methods fail to explore the contextual information within a dialogue to enrich utterance representations. In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model. Concretely, to consider the temporality of speech modality, we design a novel temporal position prediction task to capture the speech-text alignment. This pre-training task aims to predict the start and end time of each textual word in the corresponding speech waveform. In addition, to learn the characteristics of spoken dialogs, we generalize a response selection task from textual dialog pre-training to speech-text dialog pre-training scenarios. Experimental results on four different downstream speech-text tasks demonstrate the superiority of SPECTRA in learning speech-text alignment and multi-turn dialog context.

cs.CL↗

arXiv2023

Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification

The popularity of Deep Learning (DL), coupled with network traffic visibility reduction due to the increased adoption of HTTPS, QUIC and DNS-SEC, re-ignited interest towards Traffic Classification (TC). However, to tame the dependency from task-specific large labeled datasets we need to find better ways to learn representations that are valid across tasks. In this work we investigate this problem comparing transfer learning, meta-learning and contrastive learning against reference Machine Learning (ML) tree-based and monolithic DL models (16 methods total). Using two publicly available datasets, namely MIRAGE19 (40 classes) and AppClassNet (500 classes), we show that (i) using large datasets we can obtain more general representations, (ii) contrastive learning is the best methodology and (iii) meta-learning the worst one, and (iv) while ML tree-based cannot handle large tasks but fits well small tasks, by means of reusing learned representations, DL methods are reaching tree-based models performance also for small tasks.

cs.LG↗

arXiv2023

Preference or Intent? Double Disentangled Collaborative Filtering

People usually have different intents for choosing items, while their preferences under the same intent may also different. In traditional collaborative filtering approaches, both intent and preference factors are usually entangled in the modeling process, which significantly limits the robustness and interpretability of recommendation performances. For example, the low-rating items are always treated as negative feedback while they actually could provide positive information about user intent. To this end, in this paper, we propose a two-fold representation learning approach, namely Double Disentangled Collaborative Filtering (DDCF), for personalized recommendations. The first-level disentanglement is for separating the influence factors of intent and preference, while the second-level disentanglement is performed to build independent sparse preference representations under individual intent with limited computational complexity. Specifically, we employ two variational autoencoder networks, intent recognition network and preference decomposition network, to learn the intent and preference factors, respectively. In this way, the low-rating items will be treated as positive samples for modeling intents while the negative samples for modeling preferences. Finally, extensive experiments on three real-world datasets and four evaluation metrics clearly validate the effectiveness and the interpretability of DDCF.

cs.IR↗

arXiv2023

An Improved QFT-Based Quantum Comparator and Extended Modular Arithmetic Using One Ancilla Qubit

Quantum comparators and modular arithmetic are fundamental in many quantum algorithms. Current research mainly focuses on operations between two quantum states. However, various applications, such as integer factorization, optimization, option pricing, and risk analysis, commonly require one of the inputs to be classical. It requires many ancillary qubits, especially when subsequent computations are involved. In this paper, we propose a quantum-classical comparator based on the quantum Fourier transform (QFT). Then we extend it to compare two quantum integers and modular arithmetic. Proposed operators only require one ancilla qubit, which is optimal for qubit resources. We analyze limitations in the current modular addition circuit and develop it to process arbitrary quantum states in the entire $n$-qubit space. The proposed algorithms reduce computing resources and make them valuable for Noisy Intermediate-Scale Quantum (NISQ) computers.

quant-ph↗

arXiv2023

Zero-viscosity limit of the compressible Naiver-Stokes equations in the analytic setting

In this paper, we study the zero-viscosity limit of the compressible Navier-Stokes equations in a half-space with non-slip boundary condition. We justify the Prandtl boundary layer expansion for the analytic data: the compressible Navier-Stokes equations can be approximated by the compressible Euler equations away from the boundary, and by the compressible Prandtl equation near the boundary.

math.AP↗

arXiv2023

Towards Complex Document Understanding By Discrete Reasoning

Document Visual Question Answering (VQA) aims to understand visually-rich documents to answer questions in natural language, which is an emerging research topic for both Natural Language Processing and Computer Vision. In this work, we introduce a new Document VQA dataset, named TAT-DQA, which consists of 3,067 document pages comprising semi-structured table(s) and unstructured text as well as 16,558 question-answer pairs by extending the TAT-QA dataset. These documents are sampled from real-world financial reports and contain lots of numbers, which means discrete reasoning capability is demanded to answer questions on this dataset. Based on TAT-DQA, we further develop a novel model named MHST that takes into account the information in multi-modalities, including text, layout and visual image, to intelligently address different types of questions with corresponding strategies, i.e., extraction or reasoning. Extensive experiments show that the MHST model significantly outperforms the baseline methods, demonstrating its effectiveness. However, the performance still lags far behind that of expert humans. We expect that our new TAT-DQA dataset would facilitate the research on deep understanding of visually-rich documents combining vision and language, especially for scenarios that require discrete reasoning. Also, we hope the proposed model would inspire researchers to design more advanced Document VQA models in future. Our dataset will be publicly available for non-commercial use at https://nextplusplus.github.io/TAT-DQA/.

cs.CV↗

arXiv2023

An alternative simulation approach for surface flashover in vacuum using a 1D2V continuum and kinetic model

Surface flashover across insulator in vacuum is a destructive plasma discharge which undermines the behaviors of a range of applications in electrical engineering, particle physics, space engineering, etc. This phenomenon is widely modeled by the particle-in-cell (PIC) simulation, here the continuum and kinetic simulation method is first proposed and implemented as an alternative solution for flashover modeling, aiming for the prevention of the unfavorable particle noises in PIC models. The 1D2V (one dimension in space, two dimensions in velocity) kinetic simulation model is constructed. Modeling setup, physical assumptions, and simulation algorithm are presented in detail, and a comparison with the well-known secondary electron emission avalanche (SEEA) analytical expression and existing PIC simulation is made. Obtained kinetic simulation results are consistent with the analytical prediction, and feature noise-free data of surface charge density as well as particle fluxes of primary and secondary electrons. Discrepancies between the two simulation models and analytical predictions are explained. The code is convenient for updating to include additional physical processes, and possible implementations of outgassing and extra plasma species for final breakdown stage are discussed. The proposed continuum and kinetic approach is expected to inspire future flashover modeling studies for the understanding and mitigation.

physics.plasm-ph↗