arXiv subjects

Ziyuan Wang

Publications and source records attributed to Ziyuan Wang.

At least 55 records · Page 3Linked to original sources

arXiv2023

ChinaOpen: A Dataset for Open-world Multimodal Learning

This paper introduces ChinaOpen, a dataset sourced from Bilibili, a popular Chinese video-sharing website, for open-world multimodal learning. While the state-of-the-art multimodal learning networks have shown impressive performance in automated video annotation and cross-modal video retrieval, their training and evaluation are primarily conducted on YouTube videos with English text. Their effectiveness on Chinese data remains to be verified. In order to support multimodal learning in the new context, we construct ChinaOpen-50k, a webly annotated training set of 50k Bilibili videos associated with user-generated titles and tags. Both text-based and content-based data cleaning are performed to remove low-quality videos in advance. For a multi-faceted evaluation, we build ChinaOpen-1k, a manually labeled test set of 1k videos. Each test video is accompanied with a manually checked user title and a manually written caption. Besides, each video is manually tagged to describe objects / actions / scenes shown in the visual content. The original user tags are also manually checked. Moreover, with all the Chinese text translated into English, ChinaOpen-1k is also suited for evaluating models trained on English data. In addition to ChinaOpen, we propose Generative Video-to-text Transformer (GVT) for Chinese video captioning. We conduct an extensive evaluation of the state-of-the-art single-task / multi-task models on the new dataset, resulting in a number of novel findings and insights.

cs.MM↗

arXiv2023

Every proximal mapping is a resolvent of level proximal subdifferential

We propose a level proximal subdifferential for a proper lower semicontinuous function. Level proximal subdifferential is a uniform refinement of the well-known proximal subdifferential, and has the pleasant feature that its resolvent always coincides with the proximal mapping of a function. It turns out that the resolvent representation of proximal mapping in terms of Mordukhovich limiting subdifferential is only valid for hypoconvex functions. We also provide properties of level proximal subdifferential and numerous examples to illustrate our results.

math.OC↗

arXiv2023

How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection

The introduction of ChatGPT has garnered widespread attention in both academic and industrial communities. ChatGPT is able to respond effectively to a wide range of human questions, providing fluent and comprehensive answers that significantly surpass previous public chatbots in terms of security and usefulness. On one hand, people are curious about how ChatGPT is able to achieve such strength and how far it is from human experts. On the other hand, people are starting to worry about the potential negative impacts that large language models (LLMs) like ChatGPT could have on society, such as fake news, plagiarism, and social security issues. In this work, we collected tens of thousands of comparison responses from both human experts and ChatGPT, with questions ranging from open-domain, financial, medical, legal, and psychological areas. We call the collected dataset the Human ChatGPT Comparison Corpus (HC3). Based on the HC3 dataset, we study the characteristics of ChatGPT's responses, the differences and gaps from human experts, and future directions for LLMs. We conducted comprehensive human evaluations and linguistic analyses of ChatGPT-generated content compared with that of humans, where many interesting results are revealed. After that, we conduct extensive experiments on how to effectively detect whether a certain text is generated by ChatGPT or humans. We build three different detection systems, explore several key factors that influence their effectiveness, and evaluate them in different scenarios. The dataset, code, and models are all publicly available at https://github.com/Hello-SimpleAI/chatgpt-comparison-detection.

cs.CL↗

arXiv2022

A mirror inertial forward-reflected-backward splitting: Global convergence and linesearch extension beyond convexity and Lipschitz smoothness

This work investigates a Bregman and inertial extension of the forward-reflected-backward algorithm [Y. Malitsky and M. Tam, SIAM J. Optim., 30 (2020), pp. 1451--1472] applied to structured nonconvex minimization problems under relative smoothness. To this end, the proposed algorithm hinges on two key features: taking inertial steps in the dual space, and allowing for possibly negative inertial values. Our analysis begins with studying an associated envelope function that takes inertial terms into account through a novel product space formulation. Such construction substantially differs from similar objects in the literature and could offer new insights for extensions of splitting algorithms. Global convergence and rates are obtained by appealing to the generalized concave Kurdyka-Lojasiewicz (KL) property, which allows us to describe a sharp upper bound on the total length of iterates. Finally, a linesearch extension is given to enhance the proposed method.

math.OC↗

arXiv2022

SAS: A Simple, Accurate and Scalable Node Classification Algorithm

Graph neural networks have achieved state-of-the-art accuracy for graph node classification. However, GNNs are difficult to scale to large graphs, for example frequently encountering out-of-memory errors on even moderate size graphs. Recent works have sought to address this problem using a two-stage approach, which first aggregates data along graph edges, then trains a classifier without using additional graph information. These methods can run on much larger graphs and are orders of magnitude faster than GNNs, but achieve lower classification accuracy. We propose a novel two-stage algorithm based on a simple but effective observation: we should first train a classifier then aggregate, rather than the other way around. We show our algorithm is faster and can handle larger graphs than existing two-stage algorithms, while achieving comparable or higher accuracy than popular GNNs. We also present a theoretical basis to explain our algorithm's improved accuracy, by giving a synthetic nonlinear dataset in which performing aggregation before classification actually decreases accuracy compared to doing classification alone, while our classify then aggregate approach substantially improves accuracy compared to classification alone.

cs.LG↗

arXiv2022

IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification

Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in the label text. As a matter of fact, humans classify documents primarily based on the semantic meaning of the subcategories. We propose a novel model structure via siamese BERT and interactive double attentions named IDEA ( Interactive DoublE Attentions) to capture the information exchange of text and label names. Interactive double attentions enable the model to exploit the inter-class and intra-class information from coarse to fine, which involves distinguishing among all labels and matching the semantical subclasses of ground truth labels. Our proposed method outperforms the state-of-the-art methods using label texts significantly with more stable results.

cs.CL↗

arXiv2022

A Bregman inertial forward-reflected-backward method for nonconvex minimization

We propose a Bregman inertial forward-reflected-backward (BiFRB) method for nonconvex composite problems. Our analysis relies on a novel approach that imposes general conditions on implicit merit function parameters, which yields a stepsize condition that is independent of inertial parameters. In turn, a question of Malitsky and Tam regarding whether FRB can be equipped with a Nesterov-type acceleration is resolved. Assuming the generalized concave Kurdyka-Łojasiewicz property of a quadratic regularization of the objective, we obtain sequential convergence of BiFRB, as well as convergence rates on both the function value and actual sequence. We also present formulae for the Bregman subproblem, supplementing not only BiFRB but also the work of Boţ-Csetnek-László and Boţ-Csetnek. Numerical simulations are conducted to evaluate the performance of our proposed algorithm.

math.OC↗

arXiv2022

Test suite effectiveness metric evaluation: what do we know and what should we do?

Comparing test suite effectiveness metrics has always been a research hotspot. However, prior studies have different conclusions or even contradict each other for comparing different test suite effectiveness metrics. The problem we found most troubling to our community is that researchers tend to oversimplify the description of the ground truth they use. For example, a common expression is that "we studied the correlation between real faults and the metric to evaluate (MTE)". However, the meaning of "real faults" is not clear-cut. As a result, there is a need to scrutinize the meaning of "real faults". Without this, it will be half-knowledgeable with the conclusions. To tackle this challenge, we propose a framework ASSENT (evAluating teSt Suite EffectiveNess meTrics) to guide the follow-up research. In nature, ASSENT consists of three fundamental components: ground truth, benchmark test suites, and agreement indicator. First, materialize the ground truth for determining the real order in effectiveness among test suites. Second, generate a set of benchmark test suites and derive their ground truth order in effectiveness. Third, for the benchmark test suites, generate the MTE order in effectiveness by the metric to evaluate (MTE). Finally, calculate the agreement indicator between the two orders. Under ASSENT, we are able to compare the accuracy of different test suite effectiveness metrics. We apply ASSENT to evaluate representative test suite effectiveness metrics, including mutation score metrics and code coverage metrics. Our results show that, based on the real faults, mutation score and subsuming mutation score are the best metrics to quantify test suite effectiveness. Meanwhile, by using mutants instead of real faults, MTEs will be overestimated by more than 20% in values.

cs.SE↗

arXiv2022

Program Repair: Automated vs. Manual

Various automated program repair (APR) techniques have been proposed to fix bugs automatically in the last decade. Although recent researches have made significant progress on the effectiveness and efficiency, it is still unclear how APR techniques perform with human intervention in a real debugging scenario. To bridge this gap, we conduct an extensive study to compare three state-of-the-art APR tools with manual program repair, and further investigate whether the assistance of APR tools (i.e., repair reports) can improve manual program repair. To that end, we recruit 20 participants for a controlled experiment, resulting in a total of 160 manual repair tasks and a questionnaire survey. The experiment reveals several notable observations that (1) manual program repair may be influenced by the frequency of repair actions sometimes; (2) APR tools are more efficient in terms of debugging time, while manual program repair tends to generate a correct patch with fewer attempts; (3) APR tools can further improve manual program repair regarding the number of correctly-fixed bugs, while there exists a negative impact on the patch correctness; (4) participants are used to consuming more time to identify incorrect patches, while they are still misguided easily; (5) participants are positive about the tools' repair performance, while they generally lack confidence about the usability in practice. Besides, we provide some guidelines for improving the usability of APR tools (e.g., the misleading information in reports and the observation of feedback).

cs.SE↗

arXiv2021

Malitsky-Tam forward-reflected-backward splitting method for nonconvex minimization problems

We extend the Malitsky-Tam forward-reflected-backward (FRB) splitting method for inclusion problems of monotone operators to nonconvex minimization problems. By assuming the generalized concave Kurdyka-Łojasiewicz (KL) property of a quadratic regularization of the objective, we show that the FRB method converges globally to a stationary point of the objective and enjoys finite length property. The sharpness of our approach is guaranteed by virtue of the exact modulus associated with the generalized concave KL property. Numerical experiments suggest that FRB is competitive compared to the Douglas-Rachford method and the Boţ-Csetnek inertial Tseng's method.

math.OC↗

arXiv2021

The exact modulus of the generalized concave Kurdyka-Łojasiewicz property

We introduce a generalized version of the concave Kurdyka-Łojasiewicz (KL) property by employing nonsmooth desingularizing functions. We also present the exact modulus of the generalized concave KL property, which provides an answer to the open question regarding the optimal concave desingularizing function. The exact modulus is designed to be the smallest among all possible concave desingularizing functions. Examples are given to illustrate this pleasant property. In turn, using the exact modulus we provide the sharpest upper bound for the total length of iterates generated by the celebrated Bolte-Sabach-Teboulle PALM algorithm.

math.OC↗

arXiv2021

Calculus rules of the generalized concave Kurdyka-Łojasiewicz property

In this paper, we propose several calculus rules for the generalized concave Kurdyka-Łojasiewicz (KL) property, which generalize Li and Pong's results for KL exponents. The optimal concave desingularizing function has various forms and may be nondifferentiable. Our calculus rules do not assume desingularizing functions to have any specific form nor differentiable, while the known results do. Several examples are also given to show that our calculus rules are applicable to a broader class of functions than the known ones.

math.OC↗

arXiv2021

Dynamics in the transition region beneath active region upflows viewed by IRIS

Coronal upflows at the edges of active regions (AR), which are a possible source of slow solar wind, have been found to connect with dynamics in the transition region. To infer at what scale transition region dynamics connect to AR upflows, we investigate the statistical properties of the small-scale dynamics in the transition region underneath the upflows at the edge of AR NOAA 11934. With observations from the Interface Region Imaging Spectragraph (IRIS), we found that the Si IV 1403\,Å Doppler map consists of numerous blue-shifted and red-shifted patches mostly with sizes less than 1\,$Mm^2$. The blue-shifted structures in the transition region tend to be brighter than the red-shifted ones, but their nonthermal velocities have no significant difference. With the SWAMIS feature tracking procedure, in IRIS slit-jaw 1400\,Å images we found that dynamic bright dots with an average size of about 0.3\,$Mm^2$ and lifetimes mostly less than 200\,s spread all over the region. Most of the bright dots appear to be localised, without clear signature of propagation of plasma to a long distance on the projection plane. Surge-like motions with speeds about 15 km/s could be seen in some events at the boundaries of the upflow region, where the magnetic field appear to be inclined. We conclude that the transition region dynamics connecting to coronal upflows should occur in very fine scale, suggesting that the corresponding coronal upflows should also be highly-structured. It is also plausible that the transition region dynamics might just act as stimulation at the coronal base that then drives the upflows in the corona.

astro-ph.SR↗

arXiv2021

Decentralized Statistical Inference with Unrolled Graph Neural Networks

In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination. Existing optimization-based algorithms suffer from issues of model mismatch and poor convergence speed, and thus their performance would be degraded, provided that the number of communication rounds is limited. This motivates us to propose a learning-based framework, which unrolls well-noted decentralized optimization algorithms (e.g., Prox-DGD and PG-EXTRA) into graph neural networks (GNNs). By minimizing the recovery error via end-to-end training, this learning-based framework resolves the model mismatch issue. Our convergence analysis (with PG-EXTRA as the base algorithm) reveals that the learned model parameters may accelerate the convergence and reduce the recovery error to a large extent. The simulation results demonstrate that the proposed GNN-based learning methods prominently outperform several state-of-the-art optimization-based algorithms in convergence speed and recovery error.

cs.LG↗

arXiv2021

Mutant reduction evaluation: what is there and what is missing?

Background. Many mutation reduction strategies, which aim to reduce the number of mutants, have been proposed. Problem. It is important to measure the ability of a mutation reduction strategy to maintain test suite effectiveness evaluation. However, existing evaluation indicators are unable to measure the "order-preserving ability". Objective. We aim to propose evaluation indicators to measure the "order-preserving ability" of a mutation reduction strategy, which is important but missing in our community. Method. Given a test suite on a Software Under Test (SUT) with a set of original mutants, we leverage the test suite to generate a group of test suites that have a partial order relationship in fault detecting potential. When evaluating a reduction strategy, we first construct two partial order relationships among the generated test suites in terms of mutation score, one with the original mutants and another with the reduced mutants. Then, we measure the extent to which the two partial order relationships are consistent. The more consistent the two partial order relationships are, the stronger the Order Preservation (OP) of the mutation reduction strategy is, and the more effective the reduction strategy is. Furthermore, we propose Effort-aware Relative Order Preservation (EROP) to measure how much gain a mutation reduction strategy can provide compared with a random reduction strategy. Result. The experimental results show that OP and EROP are able to efficiently measure the "order-preserving ability" of a mutation reduction strategy. As a result, they have a better ability to distinguish various mutation reduction strategies compared with the existing evaluation indicators. Conclusion. We suggest, for the researchers, that OP and EROP should be used to measure the effectiveness of a mutant reduction strategy.

cs.SE↗

arXiv2020

Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation

Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (\ie, Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method.

eess.IV↗

arXiv2019

Machine learning for automatic construction of pseudo-realistic pediatric abdominal phantoms

Machine Learning (ML) is proving extremely beneficial in many healthcare applications. In pediatric oncology, retrospective studies that investigate the relationship between treatment and late adverse effects still rely on simple heuristics. To assess the effects of radiation therapy, treatment plans are typically simulated on phantoms, i.e., virtual surrogates of patient anatomy. Currently, phantoms are built according to reasonable, yet simple, human-designed criteria. This often results in a lack of individualization. We present a novel approach that combines imaging and ML to build individualized phantoms automatically. Given the features of a patient treated historically (only 2D radiographs available), and a database of 3D Computed Tomography (CT) imaging with organ segmentations and relative patient features, our approach uses ML to predict how to assemble a patient-specific phantom automatically. Experiments on 60 abdominal CTs of pediatric patients show that our approach constructs significantly more representative phantoms than using current phantom building criteria, in terms of location and shape of the abdomen and of two considered organs, the liver and the spleen. Among several ML algorithms considered, the Gene-pool Optimal Mixing Evolutionary Algorithm for Genetic Programming (GP-GOMEA) is found to deliver the best performing models, which are, moreover, transparent and interpretable mathematical expressions.

cs.LG↗

arXiv2019

From Data Quality to Model Quality: an Exploratory Study on Deep Learning

Nowadays, people strive to improve the accuracy of deep learning models. However, very little work has focused on the quality of data sets. In fact, data quality determines model quality. Therefore, it is important for us to make research on how data quality affects on model quality. In this paper, we mainly consider four aspects of data quality, including Dataset Equilibrium, Dataset Size, Quality of Label, Dataset Contamination. We deign experiment on MNIST and Cifar-10 and try to find out the influence the four aspects make on model quality. Experimental results show that four aspects all have decisive impact on the quality of models. It means that decrease in data quality in these aspects will reduce the accuracy of model.

cs.LG↗