arXiv subjects

Yuwei Zhang

Publications and source records attributed to Yuwei Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2024

Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking

Respiratory audio, such as coughing and breathing sounds, has predictive power for a wide range of healthcare applications, yet is currently under-explored. The main problem for those applications arises from the difficulty in collecting large labeled task-specific data for model development. Generalizable respiratory acoustic foundation models pretrained with unlabeled data would offer appealing advantages and possibly unlock this impasse. However, given the safety-critical nature of healthcare applications, it is pivotal to also ensure openness and replicability for any proposed foundation model solution. To this end, we introduce OPERA, an OPEn Respiratory Acoustic foundation model pretraining and benchmarking system, as the first approach answering this need. We curate large-scale respiratory audio datasets (~136K samples, over 400 hours), pretrain three pioneering foundation models, and build a benchmark consisting of 19 downstream respiratory health tasks for evaluation. Our pretrained models demonstrate superior performance (against existing acoustic models pretrained with general audio on 16 out of 19 tasks) and generalizability (to unseen datasets and new respiratory audio modalities). This highlights the great promise of respiratory acoustic foundation models and encourages more studies using OPERA as an open resource to accelerate research on respiratory audio for health. The system is accessible from https://github.com/evelyn0414/OPERA.

cs.SD↗

arXiv2024

RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction

The high incidence and mortality rates associated with respiratory diseases underscores the importance of early screening. Machine learning models can automate clinical consultations and auscultation, offering vital support in this area. However, the data involved, spanning demographics, medical history, symptoms, and respiratory audio, are heterogeneous and complex. Existing approaches are insufficient and lack generalizability, as they typically rely on limited training data, basic fusion techniques, and task-specific models. In this paper, we propose RespLLM, a novel multimodal large language model (LLM) framework that unifies text and audio representations for respiratory health prediction. RespLLM leverages the extensive prior knowledge of pretrained LLMs and enables effective audio-text fusion through cross-modal attentions. Instruction tuning is employed to integrate diverse data from multiple sources, ensuring generalizability and versatility of the model. Experiments on five real-world datasets demonstrate that RespLLM outperforms leading baselines by an average of 4.6% on trained tasks, 7.9% on unseen datasets, and facilitates zero-shot predictions for new tasks. Our work lays the foundation for multimodal models that can perceive, listen to, and understand heterogeneous data, paving the way for scalable respiratory health diagnosis.

cs.LG↗

arXiv2024

Jump Diffusion-Informed Neural Networks with Transfer Learning for Accurate American Option Pricing under Data Scarcity

Option pricing models, essential in financial mathematics and risk management, have been extensively studied and recently advanced by AI methodologies. However, American option pricing remains challenging due to the complexity of determining optimal exercise times and modeling non-linear payoffs resulting from stochastic paths. Moreover, the prevalent use of the Black-Scholes formula in hybrid models fails to accurately capture the discontinuity in the price process, limiting model performance, especially under scarce data conditions. To address these issues, this study presents a comprehensive framework for American option pricing consisting of six interrelated modules, which combine nonlinear optimization algorithms, analytical and numerical models, and neural networks to improve pricing performance. Additionally, to handle the scarce data challenge, this framework integrates the transfer learning through numerical data augmentation and a physically constrained, jump diffusion process-informed neural network to capture the leptokurtosis of the log return distribution. To increase training efficiency, a warm-up period using Bayesian optimization is designed to provide optimal data loss and physical loss coefficients. Experimental results of six case studies demonstrate the accuracy, convergence, physical effectiveness, and generalization of the framework. Moreover, the proposed model shows superior performance in pricing deep out-of-the-money options.

cs.LG↗

arXiv2024

Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition

Human Activity Recognition (HAR) has gained great attention from researchers due to the popularity of mobile devices and the need to observe users' daily activity data for better human-computer interaction. In this work, we collect a human activity recognition dataset called OPPOHAR consisting of phone IMU data. To facilitate the employment of HAR system in mobile phone and to achieve user-specific activity recognition, we propose a novel light-weight network called Non-stationary BERT with a two-stage training method. We also propose a simple yet effective data augmentation method to explore the deeper relationship between the accelerator and gyroscope data from the IMU. The network achieves the state-of-the-art performance testing on various activity recognition datasets and the data augmentation method demonstrates its wide applicability.

cs.AI↗

arXiv2024

Effectiveness of Pre-training for Few-shot Intent Classification

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.

cs.CL↗

arXiv2024

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization

It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language models with a small amount of labeled utterances from public benchmarks in a supervised manner is extremely helpful. However, we find that supervised pre-training yields an anisotropic feature space, which may suppress the expressive power of the semantic representations. Inspired by recent research in isotropization, we propose to improve supervised pre-training by regularizing the feature space towards isotropy. We propose two regularizers based on contrastive learning and correlation matrix respectively, and demonstrate their effectiveness through extensive experiments. Our main finding is that it is promising to regularize supervised pre-training with isotropization to further improve the performance of few-shot intent detection. The source code can be found at https://github.com/fanolabs/isoIntentBert-main.

cs.CL↗

arXiv2024

Monocular Localization with Semantics Map for Autonomous Vehicles

Accurate and robust localization remains a significant challenge for autonomous vehicles. The cost of sensors and limitations in local computational efficiency make it difficult to scale to large commercial applications. Traditional vision-based approaches focus on texture features that are susceptible to changes in lighting, season, perspective, and appearance. Additionally, the large storage size of maps with descriptors and complex optimization processes hinder system performance. To balance efficiency and accuracy, we propose a novel lightweight visual semantic localization algorithm that employs stable semantic features instead of low-level texture features. First, semantic maps are constructed offline by detecting semantic objects, such as ground markers, lane lines, and poles, using cameras or LiDAR sensors. Then, online visual localization is performed through data association of semantic features and map objects. We evaluated our proposed localization framework in the publicly available KAIST Urban dataset and in scenarios recorded by ourselves. The experimental results demonstrate that our method is a reliable and practical localization solution in various autonomous driving localization tasks.

cs.CV↗

arXiv2024

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation

Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data from existing examples by only tweaking in the user-provided, task-specific attribute, e.g., sentiment polarity or topic in movie reviews. Instead of conventional latent representation controlling, we leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence reconstruction. Extensive results on various tasks, such as text (pair) classification, aspect-based sentiment analysis, and conditional text generation, verify the superiority of CoTAM over other LLM-based augmentation methods with the same number of training examples for both fine-tuning and in-context learning. Remarkably, the 2D visualization of the augmented dataset using principal component analysis revealed a human-recognizable decision boundary that is likely hinted by the attribute manipulation, demonstrating the potential of our proposed approach.

cs.CL↗

arXiv2024

Defect Category Prediction Based on Multi-Source Domain Adaptation

In recent years, defect prediction techniques based on deep learning have become a prominent research topic in the field of software engineering. These techniques can identify potential defects without executing the code. However, existing approaches mostly concentrate on determining the presence of defects at the method-level code, lacking the ability to precisely classify specific defect categories. Consequently, this undermines the efficiency of developers in locating and rectifying defects. Furthermore, in practical software development, new projects often lack sufficient defect data to train high-accuracy deep learning models. Models trained on historical data from existing projects frequently struggle to achieve satisfactory generalization performance on new projects. Hence, this paper initially reformulates the traditional binary defect prediction task into a multi-label classification problem, employing defect categories described in the Common Weakness Enumeration (CWE) as fine-grained predictive labels. To enhance the model performance in cross-project scenarios, this paper proposes a multi-source domain adaptation framework that integrates adversarial training and attention mechanisms. Specifically, the proposed framework employs adversarial training to mitigate domain (i.e., software projects) discrepancies, and further utilizes domain-invariant features to capture feature correlations between each source domain and the target domain. Simultaneously, the proposed framework employs a weighted maximum mean discrepancy as an attention mechanism to minimize the representation distance between source and target domain features, facilitating model in learning more domain-independent features. The experiments on 8 real-world open-source projects show that the proposed approach achieves significant performance improvements compared to state-of-the-art baselines.

cs.SE↗

arXiv2024

CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations

Object detection methods under known single degradations have been extensively investigated. However, existing approaches require prior knowledge of the degradation type and train a separate model for each, limiting their practical applications in unpredictable environments. To address this challenge, we propose a chain-of-thought (CoT) prompted adaptive enhancer, CPA-Enhancer, for object detection under unknown degradations. Specifically, CPA-Enhancer progressively adapts its enhancement strategy under the step-by-step guidance of CoT prompts, that encode degradation-related information. To the best of our knowledge, it's the first work that exploits CoT prompting for object detection tasks. Overall, CPA-Enhancer is a plug-and-play enhancement model that can be integrated into any generic detectors to achieve substantial gains on degraded images, without knowing the degradation type priorly. Experimental results demonstrate that CPA-Enhancer not only sets the new state of the art for object detection but also boosts the performance of other downstream vision tasks under unknown degradations.

cs.CV↗

arXiv2024

Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders

Conversational systems often rely on embedding models for intent classification and intent clustering tasks. The advent of Large Language Models (LLMs), which enable instructional embeddings allowing one to adjust semantics over the embedding space using prompts, are being viewed as a panacea for these downstream conversational tasks. However, traditional evaluation benchmarks rely solely on task metrics that don't particularly measure gaps related to semantic understanding. Thus, we propose an intent semantic toolkit that gives a more holistic view of intent embedding models by considering three tasks -- (1) intent classification, (2) intent clustering, and (3) a novel triplet task. The triplet task gauges the model's understanding of two semantic concepts paramount in real-world conversational systems -- negation and implicature. We observe that current embedding models fare poorly in semantic understanding of these concepts. To address this, we propose a pre-training approach to improve the embedding model by leveraging augmentation with data generated by an auto-regressive model and a contrastive loss term. Our approach improves the semantic understanding of the intent embedding model on the aforementioned linguistic dimensions while slightly effecting their performance on downstream task metrics.

cs.CL↗

arXiv2024

A Survey of Resilient Coordination for Cyber-Physical Systems Against Malicious Attacks

Cyber-physical systems (CPSs) facilitate the integration of physical entities and cyber infrastructures through the utilization of pervasive computational resources and communication units, leading to improved efficiency, automation, and practical viability in both academia and industry. Due to its openness and distributed characteristics, a critical issue prevalent in CPSs is to guarantee resilience in presence of malicious attacks. This paper conducts a comprehensive survey of recent advances on resilient coordination for CPSs. Different from existing survey papers, we focus on the node injection attack and propose a novel taxonomy according to the multi-layered framework of CPS. Furthermore, miscellaneous resilient coordination problems are discussed in this survey. Specifically, some preliminaries and the fundamental problem settings are given at the beginning. Subsequently, based on a multi-layered framework of CPSs, promising results of resilient consensus are classified and reviewed from three perspectives: physical structure, communication mechanism, and network topology. Next, two typical application scenarios, i.e., multi-robot systems and smart grids are exemplified to extend resilient consensus to other coordination tasks. Particularly, we examine resilient containment and resilient distributed optimization problems, both of which demonstrate the applicability of resilient coordination approaches. Finally, potential avenues are highlighted for future research.

eess.SY↗

arXiv2024

Answer is All You Need: Instruction-following Text Embedding via Answering the Question

This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embeddings, none of previous approaches provides a concrete solution for it. This paper offers a new viewpoint, which treats the instruction as a question about the input text and encodes the expected answers to obtain the representation accordingly. Intuitively, texts with the same (implicit) semantics would share similar answers following the instruction, thus leading to more similar embeddings. Specifically, we propose InBedder that instantiates this embed-via-answering idea by only fine-tuning language models on abstractive question answering tasks. InBedder demonstrates significantly improved instruction-following capabilities according to our proposed instruction awareness tests and instruction robustness tests, when applied to both large language models (LLMs) (e.g., llama-2-7b) and smaller encoder-based LMs (e.g., roberta-large). Additionally, our qualitative analysis of clustering outcomes, achieved by applying different instructions to the same corpus, demonstrates a high degree of interpretability.

cs.CL↗

arXiv2024

A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network

This work presents the first fabricated electrophysiology-optogenetic closed-loop bidirectional brain-machine interface (CL-BBMI) system-on-chip (SoC) with electrical neural signal recording, on-chip sleep staging and optogenetic stimulation. The first multiplexer with static assignment based table lookup solution (MUXnet) for multiplier-free NN processor was proposed. A state-of-the-art average accuracy of 82.4% was achieved with an energy consumption of only 0.2$μ$J/class in sleep staging task.

eess.SP↗

arXiv2023

ClusterLLM: Large Language Models as a Guide for Text Clustering

We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions , where A, B and C are similar data points that belong to different clusters according to small embedder. We empirically show that this strategy is both effective for fine-tuning small embedder and cost-efficient to query ChatGPT. Second, we prompt ChatGPT for helps on clustering granularity by carefully designed pairwise questions , and tune the granularity from cluster hierarchies that is the most consistent with the ChatGPT answers. Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of ~$0.6 per dataset. The code will be available at https://github.com/zhang-yu-wei/ClusterLLM.

cs.CL↗

arXiv2023

STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing

Bug fixing holds significant importance in software development and maintenance. Recent research has made notable progress in exploring the potential of large language models (LLMs) for automatic bug fixing. However, existing studies often overlook the collaborative nature of bug resolution, treating it as a single-stage process. To overcome this limitation, we introduce a novel stage-wise framework named STEAM in this paper. The objective of STEAM is to simulate the interactive behavior of multiple programmers involved in various stages across the bug's life cycle. Taking inspiration from bug management practices, we decompose the bug fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to imitate the collaborative abilities of programmers during the resolution of software bugs. By harnessing the collective contribution, STEAM effectively enhances the bug-fixing capabilities of LLMs. We implement STEAM by employing the powerful dialogue-based LLM -- ChatGPT. Our evaluation on the widely adopted bug-fixing benchmark demonstrates that STEAM has achieved a new state-of-the-art level of bug-fixing performance.

cs.SE↗

arXiv2023

Automated Static Warning Identification via Path-based Semantic Representation

Despite their ability to aid developers in detecting potential defects early in the software development life cycle, static analysis tools often suffer from precision issues (i.e., high false positive rates of reported alarms). To improve the availability of these tools, many automated warning identification techniques have been proposed to assist developers in classifying false positive alarms. However, existing approaches mainly focus on using hand-engineered features or statement-level abstract syntax tree token sequences to represent the defective code, failing to capture semantics from the reported alarms. To overcome the limitations of traditional approaches, this paper employs deep neural networks' powerful feature extraction and representation abilities to generate code semantics from control flow graph paths for warning identification. The control flow graph abstractly represents the execution process of a given program. Thus, the generated path sequences of the control flow graph can guide the deep neural networks to learn semantic information about the potential defect more accurately. In this paper, we fine-tune the pre-trained language model to encode the path sequences and capture the semantic representations for model building. Finally, this paper conducts extensive experiments on eight open-source projects to verify the effectiveness of the proposed approach by comparing it with the state-of-the-art baselines.

cs.SE↗

arXiv2023

SAGA: Summarization-Guided Assert Statement Generation

Generating meaningful assert statements is one of the key challenges in automated test case generation, which requires understanding the intended functionality of the tested code. Recently, deep learning-based models have shown promise in improving the performance of assert statement generation. However, existing models only rely on the test prefixes along with their corresponding focal methods, yet ignore the developer-written summarization. Based on our observations, the summarization contents usually express the intended program behavior or contain parameters that will appear directly in the assert statement. Such information will help existing models address their current inability to accurately predict assert statements. This paper presents a novel summarization-guided approach for automatically generating assert statements. To derive generic representations for natural language (i.e., summarization) and programming language (i.e., test prefixes and focal methods), we leverage a pre-trained language model as the reference architecture and fine-tune it on the task of assert statement generation. To the best of our knowledge, the proposed approach makes the first attempt to leverage the summarization of focal methods as the guidance for making the generated assert statements more accurate. We demonstrate the effectiveness of our approach on two real-world datasets when compared with state-of-the-art models.

cs.SE↗