arXiv subjects

Yuan Yuan

Publications and source records attributed to Yuan Yuan.

At least 145 records · Page 8Linked to original sources

arXiv2024

Z-SSMNet: Zonal-aware Self-supervised Mesh Network for Prostate Cancer Detection and Diagnosis with Bi-parametric MRI

Bi-parametric magnetic resonance imaging (bpMRI) has become a pivotal modality in the detection and diagnosis of clinically significant prostate cancer (csPCa). Developing AI-based systems to identify csPCa using bpMRI can transform PCa management by improving efficiency and cost-effectiveness. However, current state-of-the-art methods using convolutional neural networks (CNNs) are limited in learning in-plane and three-dimensional spatial information from anisotropic images. Their performances also depend on the availability of large, diverse, and well-annotated bpMRI datasets. We propose a Zonal-aware Self-supervised Mesh Network (Z-SSMNet) that adaptively integrates multi-dimensional (2D/2.5D/3D) convolutions to learn dense intra-slice information and sparse inter-slice information of the anisotropic bpMRI in a balanced manner. A self-supervised learning (SSL) technique is proposed to pre-train our network using large-scale unlabeled data to learn the appearance, texture, and structure semantics of bpMRI. It aims to capture both intra-slice and inter-slice information during the pre-training stage. Furthermore, we constrained our network to focus on the zonal anatomical regions to further improve the detection and diagnosis capability of csPCa. We conducted extensive experiments on the PI-CAI dataset comprising 10000+ multi-center and multi-scanner data. Our Z-SSMNet excelled in both lesion-level detection (AP score of 0.633) and patient-level diagnosis (AUROC score of 0.881), securing the top position in the Open Development Phase of the PI-CAI challenge and maintained strong performance, achieving an AP score of 0.690 and an AUROC score of 0.909, and securing the second-place ranking in the Closed Testing Phase.

eess.IV↗

arXiv2024

Competitive and Weighted Evolving Simplicial Complexes

A simplex-based network is referred to as a higher-order network, in which describe that the interactions can include more than two nodes. Many multicomponent interactions can be grasped through simplicial complexes, which have recently found applications in social, technological, and biological contexts. The paper first proposes a competitive evolving model of higher-order networks. We introduce the difference equation analysis approach in the high-order network to make the analysis network more rigorous. It avoids the assumption that the degrees of nodes are continuous in the traditional analysis network. We obtain an analytical expression for the distribution of higher-order degrees by employing the theory of Poisson processes. The established results indicate that in a d-order network the scale-free behavior for the (d-1)-dim simplex with respect to the d-order degree is controlled by the competitiveness factor. As the competitiveness increases, the d-order degree of the (d-1)-dim simplex is bent under the logarithmic coordinates. While the e(<d-1)-dim simplex with respect to the d-order degree exhibits scale-free behavior. Second, by considering the weight changes of the neighboring simplices, as triggered by the selected simplex, a new weighted evolving model in higher-order networks is proposed. The results of the competitive evolving model of higher-order networks are used to analyze the weighted evolving model so that obtained are the analytical expressions of the higher-order degree distribution and higher-order strength density function of weighted higher-order networks. The outcomes of the simulation experiments are consistent with the theoretical analysis.

physics.soc-ph↗

arXiv2024

Revisiting Evolutionary Program Repair via Code Language Model

Software defects are an inherent part of software development and maintenance. To address these defects, Automated Program Repair (APR) has been developed to fix bugs automatically. With the advent of Large Language Models, Code Language Models (CLMs) trained on code corpora excels in code generation, making them suitable for APR applications. Despite this progress, a significant limitation remains: many bugs necessitate multi-point edits for repair, yet current CLM-based APRs are restricted to single-point bug fixes, which severely narrows the scope of repairable bugs. Moreover, these tools typically only consider the direct context of the buggy line when building prompts for the CLM, leading to suboptimal repair outcomes due to the limited information provided. This paper introduces a novel approach, ARJA-CLM, which integrates the multiobjective evolutionary algorithm with CLM to fix multilocation bugs in Java projects. We also propose a context-aware prompt construction stratege, which enriches the prompt with additional information about accessible fields and methods for the CLM generating candidate statements. Our experiments on the Defects4J and APR-2024 competition benchmark demonstrate that ARJA-CLM surpasses many state-of-the-art repair systems, and performs well on multi-point bugs. The results also reveal that CLMs effectively utilize the provided field and method information within context-aware prompts to produce candidate statements.

cs.SE↗

arXiv2024

Quantum-inspired Interpretable Deep Learning Architecture for Text Sentiment Analysis

Text has become the predominant form of communication on social media, embedding a wealth of emotional nuances. Consequently, the extraction of emotional information from text is of paramount importance. Despite previous research making some progress, existing text sentiment analysis models still face challenges in integrating diverse semantic information and lack interpretability. To address these issues, we propose a quantum-inspired deep learning architecture that combines fundamental principles of quantum mechanics (QM principles) with deep learning models for text sentiment analysis. Specifically, we analyze the commonalities between text representation and QM principles to design a quantum-inspired text representation method and further develop a quantum-inspired text embedding layer. Additionally, we design a feature extraction layer based on long short-term memory (LSTM) networks and self-attention mechanisms (SAMs). Finally, we calculate the text density matrix using the quantum complex numbers principle and apply 2D-convolution neural networks (CNNs) for feature condensation and dimensionality reduction. Through a series of visualization, comparative, and ablation experiments, we demonstrate that our model not only shows significant advantages in accuracy and efficiency compared to previous related models but also achieves a certain level of interpretability by integrating QM principles. Our code is available at QISA.

cs.CV↗

arXiv2024

Photonic KAN: a Kolmogorov-Arnold network inspired efficient photonic neuromorphic architecture

Kolmogorov-Arnold Networks (KAN) models were recently proposed and claimed to provide improved parameter scaling and interpretability compared to conventional multilayer perceptron (MLP) models. Inspired by the KAN architecture, we propose the Photonic KAN -- an integrated all-optical neuromorphic platform leveraging highly parametric optical nonlinear transfer functions along KAN edges. In this work, we implement such nonlinearities in the form of cascaded ring-assisted Mach-Zehnder Interferometer (MZI) devices. This innovative design has the potential to address key limitations of current photonic neural networks. In our test cases, the Photonic KAN showcases enhanced parameter scaling and interpretability compared to existing photonic neural networks. The photonic KAN achieves approximately 65$\times$ reduction in energy consumption and area, alongside a 50$\times$ reduction in latency compared to previous MZI-based photonic accelerators with similar performance for function fitting task. This breakthrough presents a promising new avenue for expanding the scalability and efficiency of neuromorphic hardware platforms.

physics.optics↗

arXiv2024

"The Strength of Weak Ties" Varies Across Viral Channels

The diffusion of novel information through social networks is essential for dismantling echo chambers and promoting innovation. Our study examines how two major types of viral channels, specifically Direct Messaging (DM) and Broadcasting (BC), impact the well-known "strength of weak ties" in disseminating novel information across social networks. We conducted a large-scale empirical analysis, examining the sharing behavior of 500,000 users over a two-month period on a major social media platform. Our results suggest a greater capacity for DM to transmit novel information compared to BC, although DM typically involves stronger ties. Furthermore, the "strength of weak ties" is only evident in BC, not in DM where weaker ties do not transmit significantly more novel information. Our mechanism analysis indicates that the content selection by both senders and recipients, contingent on tie strength, contributes to the observed differences between these two channels. These findings expand both our understanding of contemporary weak tie theory and our knowledge of how to disseminate novel information in social networks.

econ.GN↗

arXiv2024

Application of Superconducting Technology in the Electricity Industry: A Game-Theoretic Analysis of Government Subsidy Policies and Power Company Equipment Upgrade Decisions

This study investigates the potential impact of "LK-99," a novel material developed by a Korean research team, on the power equipment industry. Using evolutionary game theory, the interactions between governmental subsidies and technology adoption by power companies are modeled. A key innovation of this research is the introduction of sensitivity analyses concerning time delays and initial subsidy amounts, which significantly influence the strategic decisions of both government and corporate entities. The findings indicate that these factors are critical in determining the rate of technology adoption and the efficiency of the market as a whole. Due to existing data limitations, the study offers a broad overview of likely trends and recommends the inclusion of real-world data for more precise modeling once the material demonstrates room-temperature superconducting characteristics. The research contributes foundational insights valuable for future policy design and has significant implications for advancing the understanding of technology adoption and market dynamics.

math.DS↗

arXiv2024

Multi-Scale Simulation of Complex Systems: A Perspective of Integrating Knowledge and Data

Complex system simulation has been playing an irreplaceable role in understanding, predicting, and controlling diverse complex systems. In the past few decades, the multi-scale simulation technique has drawn increasing attention for its remarkable ability to overcome the challenges of complex system simulation with unknown mechanisms and expensive computational costs. In this survey, we will systematically review the literature on multi-scale simulation of complex systems from the perspective of knowledge and data. Firstly, we will present background knowledge about simulating complex system simulation and the scales in complex systems. Then, we divide the main objectives of multi-scale modeling and simulation into five categories by considering scenarios with clear scale and scenarios with unclear scale, respectively. After summarizing the general methods for multi-scale simulation based on the clues of knowledge and data, we introduce the adopted methods to achieve different objectives. Finally, we introduce the applications of multi-scale simulation in typical matter systems and social systems.

eess.SY↗

arXiv2024

Improving GBDT Performance on Imbalanced Datasets: An Empirical Study of Class-Balanced Loss Functions

Class imbalance remains a significant challenge in machine learning, particularly for tabular data classification tasks. While Gradient Boosting Decision Trees (GBDT) models have proven highly effective for such tasks, their performance can be compromised when dealing with imbalanced datasets. This paper presents the first comprehensive study on adapting class-balanced loss functions to three GBDT algorithms across various tabular classification tasks, including binary, multi-class, and multi-label classification. We conduct extensive experiments on multiple datasets to evaluate the impact of class-balanced losses on different GBDT models, establishing a valuable benchmark. Our results demonstrate the potential of class-balanced loss functions to enhance GBDT performance on imbalanced datasets, offering a robust approach for practitioners facing class imbalance challenges in real-world applications. Additionally, we introduce a Python package that facilitates the integration of class-balanced loss functions into GBDT workflows, making these advanced techniques accessible to a wider audience.

cs.LG↗

arXiv2024

UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction

Urban spatio-temporal prediction is crucial for informed decision-making, such as traffic management, resource optimization, and emergence response. Despite remarkable breakthroughs in pretrained natural language models that enable one model to handle diverse tasks, a universal solution for spatio-temporal prediction remains challenging Existing prediction approaches are typically tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive domain-specific training data. In this study, we introduce UniST, a universal model designed for general urban spatio-temporal prediction across a wide range of scenarios. Inspired by large language models, UniST achieves success through: (i) utilizing diverse spatio-temporal data from different scenarios, (ii) effective pre-training to capture complex spatio-temporal dynamics, (iii) knowledge-guided prompts to enhance generalization capabilities. These designs together unlock the potential of building a universal model for various scenarios Extensive experiments on more than 20 spatio-temporal scenarios demonstrate UniST's efficacy in advancing state-of-the-art performance, especially in few-shot and zero-shot prediction. The datasets and code implementation are released on https://github.com/tsinghua-fib-lab/UniST.

cs.LG↗

arXiv2024

A Two-Part Machine Learning Approach to Characterizing Network Interference in A/B Testing

The reliability of controlled experiments, commonly referred to as "A/B tests," is often compromised by network interference, where the outcomes of individual units are influenced by interactions with others. Significant challenges in this domain include the lack of accounting for complex social network structures and the difficulty in suitably characterizing network interference. To address these challenges, we propose a machine learning-based method. We introduce "causal network motifs" and utilize transparent machine learning models to characterize network interference patterns underlying an A/B test on networks. Our method's performance has been demonstrated through simulations on both a synthetic experiment and a large-scale test on Instagram. Our experiments show that our approach outperforms conventional methods such as design-based cluster randomization and conventional analysis-based neighborhood exposure mapping. Our approach provides a comprehensive and automated solution to address network interference for A/B testing practitioners. This aids in informing strategic business decisions in areas such as marketing effectiveness and product customization.

stat.ML↗

arXiv2024

Federating to Grow Transformers with Constrained Resources without Model Sharing

The high resource consumption of large-scale models discourages resource-constrained users from developing their customized transformers. To this end, this paper considers a federated framework named Fed-Grow for multiple participants to cooperatively scale a transformer from their pre-trained small models. Under the Fed-Grow, a Dual-LiGO (Dual Linear Growth Operator) architecture is designed to help participants expand their pre-trained small models to a transformer. In Dual-LiGO, the Local-LiGO part is used to address the heterogeneity problem caused by the various pre-trained models, and the Global-LiGO part is shared to exchange the implicit knowledge from the pre-trained models, local data, and training process of participants. Instead of model sharing, only sharing the Global-LiGO strengthens the privacy of our approach. Compared with several state-of-the-art methods in simulation, our approach has higher accuracy, better precision, and lower resource consumption on computations and communications. To the best of our knowledge, most of the previous model-scaling works are centralized, and our work is the first one that cooperatively grows a transformer from multiple pre-trained heterogeneous models with the user privacy protected in terms of local data and models. We hope that our approach can extend the transformers to the broadly distributed scenarios and encourage more resource-constrained users to enjoy the bonus taken by the large-scale transformers.

cs.AI↗

arXiv2024

Limits to extreme event forecasting in chaotic systems

Predicting extreme events in chaotic systems, characterized by rare but intensely fluctuating properties, is of great importance due to their impact on the performance and reliability of a wide range of systems. Some examples include weather forecasting, traffic management, power grid operations, and financial market analysis, to name a few. Methods of increasing sophistication have been developed to forecast events in these systems. However, the boundaries that define the maximum accuracy of forecasting tools are still largely unexplored from a theoretical standpoint. Here, we address the question: What is the minimum possible error in the prediction of extreme events in complex, chaotic systems? We derive the minimum probability of error in extreme event forecasting along with its information-theoretic lower and upper bounds. These bounds are universal for a given problem, in that they hold regardless of the modeling approach for extreme event prediction: from traditional linear regressions to sophisticated neural network models. The limits in predictability are obtained from the cost-sensitive Fano's and Hellman's inequalities using the Rényi entropy. The results are also connected to Takens' embedding theorem using the information can't hurt inequality. Finally, the probability of error for a forecasting model is decomposed into three sources: uncertainty in the initial conditions, hidden variables, and suboptimal modeling assumptions. The latter allows us to assess whether prediction models are operating near their maximum theoretical performance or if further improvements are possible. The bounds are applied to the prediction of extreme events in the Rössler system and the Kolmogorov flow.

physics.data-an↗

arXiv2024

Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs

The powerful reasoning capabilities of large language models (LLMs) have brought revolutionary changes to many fields, but their performance in human behaviour generation has not yet been extensively explored. This gap likely emerges because the internal processes governing behavioral intentions cannot be solely explained by abstract reasoning. Instead, they are also influenced by a multitude of factors, including social norms and personal preference. Inspired by the Theory of Planned Behaviour (TPB), we develop a LLM workflow named Chain-of-Planned Behaviour (CoPB) for mobility behaviour generation, which reflects the important spatio-temporal dynamics of human activities. Through exploiting the cognitive structures of attitude, subjective norms, and perceived behaviour control in TPB, CoPB significantly enhance the ability of LLMs to reason the intention of next movement. Specifically, CoPB substantially reduces the error rate of mobility intention generation from 57.8% to 19.4%. To improve the scalability of the proposed CoPB workflow, we further explore the synergy between LLMs and mechanistic models. We find mechanistic mobility models, such as gravity model, can effectively map mobility intentions to physical mobility behaviours. The strategy of integrating CoPB with gravity model can reduce the token cost by 97.7% and achieve better performance simultaneously. Besides, the proposed CoPB workflow can facilitate GPT-4-turbo to automatically generate high quality labels for mobility behavior reasoning. We show such labels can be leveraged to fine-tune the smaller-scale, open source LLaMA 3-8B, which significantly reduces usage costs without sacrificing the quality of the generated behaviours.

cs.AI↗

arXiv2024

D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention

Cognitive Language Processing (CLP), situated at the intersection of Natural Language Processing (NLP) and cognitive science, plays a progressively pivotal role in the domains of artificial intelligence, cognitive intelligence, and brain science. Among the essential areas of investigation in CLP, Cognitive Signal Decoding (CSD) has made remarkable achievements, yet there still exist challenges related to insufficient global dynamic representation capability and deficiencies in multi-domain feature integration. In this paper, we introduce a novel paradigm for CLP referred to as Disentangled Frequency-Spatial-Temporal Attention(D-FaST). Specifically, we present an novel cognitive signal decoder that operates on disentangled frequency-space-time domain attention. This decoder encompasses three key components: frequency domain feature extraction employing multi-view attention, spatial domain feature extraction utilizing dynamic brain connection graph attention, and temporal feature extraction relying on local time sliding window attention. These components are integrated within a novel disentangled framework. Additionally, to encourage advancements in this field, we have created a new CLP dataset, MNRED. Subsequently, we conducted an extensive series of experiments, evaluating D-FaST's performance on MNRED, as well as on publicly available datasets including ZuCo, BCIC IV-2A, and BCIC IV-2B. Our experimental results demonstrate that D-FaST outperforms existing methods significantly on both our datasets and traditional CSD datasets including establishing a state-of-the-art accuracy score 78.72% on MNRED, pushing the accuracy score on ZuCo to 78.35%, accuracy score on BCIC IV-2A to 74.85% and accuracy score on BCIC IV-2B to 76.81%.

cs.LG↗

arXiv2024

Continuous Invariance Learning

Invariance learning methods aim to learn invariant features in the hope that they generalize under distributional shifts. Although many tasks are naturally characterized by continuous domains, current invariance learning techniques generally assume categorically indexed domains. For example, auto-scaling in cloud computing often needs a CPU utilization prediction model that generalizes across different times (e.g., time of a day and date of a year), where `time' is a continuous domain index. In this paper, we start by theoretically showing that existing invariance learning methods can fail for continuous domain problems. Specifically, the naive solution of splitting continuous domains into discrete ones ignores the underlying relationship among domains, and therefore potentially leads to suboptimal performance. To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains. CIL is a novel adversarial procedure that measures and controls the conditional independence between the labels and continuous domain indices given the extracted features. Our theoretical analysis demonstrates the superiority of CIL over existing invariance learning methods. Empirical results on both synthetic and real-world datasets (including data collected from production systems) show that CIL consistently outperforms strong baselines among all the tasks.

cs.LG↗

arXiv2024

Large Language Models as Test Case Generators: Performance Evaluation and Enhancement

Code generation with Large Language Models (LLMs) has been extensively studied and achieved remarkable progress. As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code. However, using LLMs as test case generators has been much less explored. Current research along this line primarily focuses on enhancing code generation with assistance from test cases generated by LLMs, while the performance of LLMs in test case generation alone has not been comprehensively examined. To bridge this gap, we conduct extensive experiments to study how well LLMs can generate high-quality test cases. We find that as the problem difficulty increases, state-of-the-art LLMs struggle to generate correct test cases, largely due to their inherent limitations in computation and reasoning. To mitigate this issue, we further propose a multi-agent framework called \emph{TestChain} that decouples the generation of test inputs and test outputs. Notably, TestChain uses a ReAct format conversation chain for LLMs to interact with a Python interpreter in order to provide more accurate test outputs. Our results indicate that TestChain outperforms the baseline by a large margin. Particularly, in terms of the accuracy of test cases, TestChain using GPT-4 as the backbone achieves a 13.84\% improvement over the baseline on the LeetCode-hard dataset.

cs.SE↗

arXiv2024

DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity

Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by 16\% of the RMSE of the whole image on the LRSS dataset. Our data and code is available at: \url{https://github.com/jinyeying/DeS3_Deshadow}

cs.CV↗