arXiv subjects

Bin Shi

Publications and source records attributed to Bin Shi.

At least 37 records · Page 2Linked to original sources

arXiv2025

Exploring the Power of Diffusion Large Language Models for Software Engineering: An Empirical Investigation

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising alternative with global bidirectional encoding and decoupled generation steps. This work presents the first comprehensive evaluation of DLLMs across the software development lifecycle, including code generation, defect detection, and program repair. On a large-scale benchmark of 52,937 tasks, 7Bparameter DLLMs outperform AR-LLMs with a 30% average accuracy improvement achieving a 113% gain on cross-file repair, while maintaining superior efficiency and reduced latency. Our results establish DLLMs as a superior paradigm for SE tasks.

cs.SE↗

arXiv2025

Lyapunov Analysis For Monotonically Forward-Backward Accelerated Algorithms

Nesterov's accelerated gradient method (NAG) achieves faster convergence than gradient descent for convex optimization but lacks monotonicity in function values. To address this, Beck and Teboulle [2009b] proposed a monotonic variant, M-NAG, and extended it to the proximal setting as M-FISTA for composite problems such as Lasso. However, establishing the linear convergence of M-NAG and M-FISTA under strong convexity remains an open problem. In this paper, we analyze M-NAG via the implicit-velocity phase representation and show that an additional assumption, either the position update or the phase-coupling relation, is necessary to fully recover the NAG iterates. The essence of M-NAG lies in controlling an auxiliary sequence to enforce non-increase. We further demonstrate that the M-NAG update alone is sufficient to construct a Lyapunov function guaranteeing linear convergence, without relying on full NAG iterates. By modifying the mixed sequence to incorporate forward-indexed gradients, we develop a new Lyapunov function that removes the kinetic energy term, enabling a direct extension to M-NAG. The required starting index depends only on the momentum parameter and not on problem constants. Finally, leveraging newly developed proximal inequalities, we extend our results to M-FISTA, establishing its linear convergence and deepening the theoretical understanding of monotonic accelerated methods.

math.OC↗

arXiv2025

Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on designing complex optimization objectives within the graph domain, overlooking the complementary value of the textual modality, whose features are often encoded by shallow embedding techniques, such as bag-of-words or skip-gram, so that semantic context related to anomalies may be missed. To unleash the enormous potential of textual modality, large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities. Nevertheless, their application to TAG anomaly detection remains nascent, and they struggle to encode high-order structural information inherent in graphs due to input length constraints. For high-quality anomaly detection in TAGs, we propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths. CoLL employs multi-LLM collaboration for evidence-augmented generation to capture anomaly-relevant contexts while delivering human-readable rationales for detected anomalies. Moreover, CoLL integrates a GNN equipped with a gating mechanism to adaptively fuse textual features with evidence while preserving high-order topological information. Extensive experiments demonstrate the superiority of CoLL, achieving an average improvement of 13.37% in AP. This study opens a new avenue for incorporating LLMs in advancing GAD.

cs.LG↗

arXiv2025

Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning

The widespread application of graph data in various high-risk scenarios has increased attention to graph anomaly detection (GAD). Faced with real-world graphs that often carry node descriptions in the form of raw text sequences, termed text-attributed graphs (TAGs), existing graph anomaly detection pipelines typically involve shallow embedding techniques to encode such textual information into features, and then rely on complex self-supervised tasks within the graph domain to detect anomalies. However, this text encoding process is separated from the anomaly detection training objective in the graph domain, making it difficult to ensure that the extracted textual features focus on GAD-relevant information, seriously constraining the detection capability. How to seamlessly integrate raw text and graph topology to unleash the vast potential of cross-modal data in TAGs for anomaly detection poses a challenging issue. This paper presents a novel end-to-end paradigm for text-attributed graph anomaly detection, named CMUCL. We simultaneously model data from both text and graph structures, and jointly train text and graph encoders by leveraging cross-modal and uni-modal multi-scale consistency to uncover potential anomaly-related information. Accordingly, we design an anomaly score estimator based on inconsistency mining to derive node-specific anomaly scores. Considering the lack of benchmark datasets tailored for anomaly detection on TAGs, we release 8 datasets to facilitate future research. Extensive evaluations show that CMUCL significantly advances in text-attributed graph anomaly detection, delivering an 11.13% increase in average accuracy (AP) over the suboptimal.

cs.LG↗

arXiv2025

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies.

cs.LG↗

arXiv2025

Feature Bank Enhancement for Distance-based Out-of-Distribution Detection

Out-of-distribution (OOD) detection is critical to ensuring the reliability of deep learning applications and has attracted significant attention in recent years. A rich body of literature has emerged to develop efficient score functions that assign high scores to in-distribution (ID) samples and low scores to OOD samples, thereby helping distinguish OOD samples. Among these methods, distance-based score functions are widely used because of their efficiency and ease of use. However, deep learning often leads to a biased distribution of data features, and extreme features are inevitable. These extreme features make the distance-based methods tend to assign too low scores to ID samples. This limits the OOD detection capabilities of such methods. To address this issue, we propose a simple yet effective method, Feature Bank Enhancement (FBE), that uses statistical characteristics from dataset to identify and constrain extreme features to the separation boundaries, therapy making the distance between samples inside and outside the distribution farther. We conducted experiments on large-scale ImageNet-1k and CIFAR-10 respectively, and the results show that our method achieves state-of-the-art performance on both benchmark. Additionally, theoretical analysis and supplementary experiments are conducted to provide more insights into our method.

cs.LG↗

arXiv2025

Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graph

Teaching large language models (LLMs) to use tools is crucial for improving their problem-solving abilities and expanding their applications. However, effectively using tools is challenging because it requires a deep understanding of tool functionalities and user intentions. Previous methods relied mainly on LLMs to generate instruction data, but the quality of these data was often insufficient. In this paper, we propose a new method that uses knowledge graphs to generate high-quality instruction data for LLMs. Knowledge graphs are manually curated datasets rich in semantic information. We begin by extracting various query pathways from a given knowledge graph, which are transformed into a broad spectrum of user queries. We then translate the relationships between entities into actionable tools and parse the pathways of each query into detailed solution steps, thereby creating high-quality instruction data. Our experiments show that fine-tuning on just a small sample of this synthetic data can significantly improve the tool utilization and overall capabilities of LLMs.

cs.LG↗

arXiv2025

Quantum Optimization via Gradient-Based Hamiltonian Descent

With rapid advancements in machine learning, first-order algorithms have emerged as the backbone of modern optimization techniques, owing to their computational efficiency and low memory requirements. Recently, the connection between accelerated gradient methods and damped heavy-ball motion, particularly within the framework of Hamiltonian dynamics, has inspired the development of innovative quantum algorithms for continuous optimization. One such algorithm, Quantum Hamiltonian Descent (QHD), leverages quantum tunneling to escape saddle points and local minima, facilitating the discovery of global solutions in complex optimization landscapes. However, QHD faces several challenges, including slower convergence rates compared to classical gradient methods and limited robustness in highly non-convex problems due to the non-local nature of quantum states. Furthermore, the original QHD formulation primarily relies on function value information, which limits its effectiveness. Inspired by insights from high-resolution differential equations that have elucidated the acceleration mechanisms in classical methods, we propose an enhancement to QHD by incorporating gradient information, leading to what we call gradient-based QHD. Gradient-based QHD achieves faster convergence and significantly increases the likelihood of identifying global solutions. Numerical simulations on challenging problem instances demonstrate that gradient-based QHD outperforms existing quantum and classical methods by at least an order of magnitude.

quant-ph↗

arXiv2025

On Pseudospectral Concentration for Rank-1 Sampling

Pseudospectral analysis serves as a powerful tool in matrix computation and the study of both linear and nonlinear dynamical systems. Among various numerical strategies, random sampling, especially in the form of rank-$1$ perturbations, offers a practical and computationally efficient approach. Moreover, due to invariance under unitary similarity, any complex matrix can be reduced to its upper triangular form, thereby simplifying the analysis. In this study. we develop a quantitative concentration theory for the pseudospectra of complex matrices under rank-$1$ random sampling perturbations, establishing a rigorous probabilistic framework for spectral characterization. First, for normal matrices, we derive a regular concentration inequality and demonstrate that the separation radius scales with the dimension as $δ_d \sim 1/\sqrt{d}$. Next, for the equivalence class of nilpotent Jordan blocks, we exploit classical probabilistic tools, specifically, the Hanson-Wright concentration inequality and the Carbery-Wright anti-concentration inequality, to obtain singular concentration bounds, and demonstrate that the separation radius exhibits the same dimension-dependent scaling. This yields a singular pseudospectral concentration framework. Finally, observing that upper triangular Toeplitz matrices can be represented via the symbolic polynomials of nilpotent Jordan blocks, we employ partial fraction decomposition of rational functions to extend the singular framework to the equivalence class of upper triangular Toeplitz matrices.

math.SP↗

arXiv2025

Out-of-Distribution Generalization on Graphs via Progressive Inference

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%.

cs.LG↗

arXiv2025

A Family of Controllable Momentum Coefficients for Forward-Backward Accelerated Algorithms

Nesterov's accelerated gradient method (NAG) marks a pivotal advancement in gradient-based optimization, achieving faster convergence compared to the vanilla gradient descent method for convex functions. However, its algorithmic complexity when applied to strongly convex functions remains unknown, as noted in the comprehensive review by Chambolle and Pock [2016]. This issue, aside from the critical step size, was addressed by Li et al. [2024b], with the monotonic case further explored by Fu and Shi [2024]. In this paper, we introduce a family of controllable momentum coefficients for forward-backward accelerated methods, focusing on the critical step size $s=1/L$. Unlike traditional linear forms, the proposed momentum coefficients follow an $α$-th power structure, where the parameter $r$ is adaptively tuned to $α$. Using a Lyapunov function specifically designed for $α$, we establish a controllable $O\left(1/k^{2α} \right)$ convergence rate for the NAG-$α$ method, provided that $r > 2α$. At the critical step size, NAG-$α$ achieves an inverse polynomial convergence rate of arbitrary degree by adjusting $r$ according to $α> 0$. We further simplify the Lyapunov function by expressing it in terms of the iterative sequences $x_k$ and $y_k$, eliminating the need for phase-space representations. This simplification enables us to extend the controllable $O \left(1/k^{2α} \right)$ rate to the monotonic variant, M-NAG-$α$, thereby enhancing optimization efficiency. Finally, by leveraging the fundamental inequality for composite functions, we extended the controllable $O\left(1/k^{2α} \right)$ rate to proximal algorithms, including the fast iterative shrinkage-thresholding algorithm (FISTA-$α$) and its monotonic counterpart (M-FISTA-$α$).

math.OC↗

arXiv2024

CLDG: Contrastive Learning on Dynamic Graphs

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively.

cs.LG↗

arXiv2024

Training a Label-Noise-Resistant GNN with Reduced Complexity

Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of incorrectly labeled nodes can substantially misguide model training. Mainstream solutions define node classification with label noise (NCLN) as a reliable labeling task, often introducing node similarity with quadratic computational complexity to more accurately assess label reliability. To this end, in this paper, we introduce the Label Ensemble Graph Neural Network (LEGNN), a lower complexity method for robust GNNs training against label noise. LEGNN reframes NCLN as a label ensemble task, gathering informative multiple labels instead of constructing a single reliable label, avoiding high-complexity computations for reliability assessment. Specifically, LEGNN conducts a two-step process: bootstrapping neighboring contexts and robust learning with gathered multiple labels. In the former step, we apply random neighbor masks for each node and gather the predicted labels as a high-probability label set. This mitigates the impact of inaccurately labeled neighbors and diversifies the label set. In the latter step, we utilize a partial label learning based strategy to aggregate the high-probability label information for model training. Additionally, we symmetrically gather a low-probability label set to counteract potential noise from the bootstrapped high-probability label set. Extensive experiments on six datasets demonstrate that LEGNN achieves outstanding performance while ensuring efficiency. Moreover, it exhibits good scalability on dataset with over one hundred thousand nodes and one million edges.

cs.LG↗

arXiv2024

Numerical Solution for Nonlinear 4D Variational Data Assimilation (4D-Var) via ADMM

The four-dimensional variational data assimilation (4D-Var) has emerged as an important methodology, widely used in numerical weather prediction, oceanographic modeling, and climate forecasting. Classical unconstrained gradient-based algorithms often struggle with local minima, making their numerical performance highly sensitive to the initial guess. In this study, we exploit the separable structure of the 4D-Var problem to propose a practical variant of the alternating direction method of multipliers (ADMM), referred to as the linearized multi-block ADMM with regularization. Unlike classical first-order optimization methods that primarily focus on initial conditions, our approach derives the Euler-Lagrange equation for the entire dynamical system, enabling more comprehensive and effective utilization of observational data. When the initial condition is poorly chosen, the arg min operation steers the iteration towards the observational data, thereby reducing sensitivity to the initial guess. The quadratic subproblems further simplify the solution process, while the parallel structure enhances computational efficiency, especially when utilizing modern hardware. To validate our approach, we demonstrate its superior performance using the Lorenz system, even in the presence of noisy observational data. Furthermore, we showcase the effectiveness of the linearized multi-block ADMM with regularization in solving the 4D-Var problems for the viscous Burgers' equation, across various numerical schemes, including finite difference, finite element, and spectral methods. Finally, we illustrate the recovery of dynamics under noisy observational data in a 2D turbulence scenario, particularly focusing on vorticity concentration, highlighting the robustness of our algorithm in handling complex physical phenomena.

math.NA↗

arXiv2024

A Lyapunov Analysis of Accelerated PDHG Algorithms

The generalized Lasso is a remarkably versatile and extensively utilized model across a broad spectrum of domains, including statistics, machine learning, and image science. Among the optimization techniques employed to address the challenges posed by this model, saddle-point methods stand out for their effectiveness. In particular, the primal-dual hybrid gradient (PDHG) algorithm has emerged as a highly popular choice, celebrated for its robustness and efficiency in finding optimal solutions. Recently, the underlying mechanism of the PDHG algorithm has been elucidated through the high-resolution ordinary differential equation (ODE) and the implicit-Euler scheme as detailed in [Li and Shi, 2024a]. This insight has spurred the development of several accelerated variants of the PDHG algorithm, originally proposed by [Chambolle and Pock, 2011]. By employing discrete Lyapunov analysis, we establish that the PDHG algorithm with iteration-varying step sizes, converges at a rate near $O(1/k^2)$. Furthermore, for the specific setting where $τ_{k+1}σ_k = s^2$ and $θ_k = τ_{k+1}/τ_k \in (0, 1)$ as proposed in [Chambolle and Pock, 2011], an even faster convergence rate of $O(1/k^2)$ can be achieved. To substantiate these findings, we design a novel discrete Lyapunov function. This function is distinguished by its succinctness and straightforwardness, providing a clear and elegant proof of the enhanced convergence properties of the PDHG algorithm under the specified conditions. Finally, we utilize the discrete Lyapunov function to establish the optimal linear convergence rate when both the objective functions are strongly convex.

math.OC↗

arXiv2024

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks.

cs.CV↗

arXiv2024

Interpretable Geoscience Artificial Intelligence (XGeoS-AI): Application to Demystify Image Recognition

As Earth science enters the era of big data, artificial intelligence (AI) not only offers great potential for solving geoscience problems, but also plays a critical role in accelerating the understanding of the complex, interactive, and multiscale processes of Earth's behavior. As geoscience AI models are progressively utilized for significant predictions in crucial situations, geoscience researchers are increasingly demanding their interpretability and versatility. This study proposes an interpretable geoscience artificial intelligence (XGeoS-AI) framework to unravel the mystery of image recognition in the Earth sciences, and its effectiveness and versatility is demonstrated by taking computed tomography (CT) image recognition as an example. Inspired by the mechanism of human vision, the proposed XGeoS-AI framework generates a threshold value from a local region within the whole image to complete the recognition. Different kinds of artificial intelligence (AI) methods, such as Support Vector Regression (SVR), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), can be adopted as the AI engines of the proposed XGeoS-AI framework to efficiently complete geoscience image recognition tasks. Experimental results demonstrate that the effectiveness, versatility, and heuristics of the proposed framework have great potential in solving geoscience image recognition problems. Interpretable AI should receive more and more attention in the field of the Earth sciences, which is the key to promoting more rational and wider applications of AI in the field of Earth sciences. In addition, the proposed interpretable framework may be the forerunner of technological innovation in the Earth sciences.

cs.CV↗

arXiv2024

Linear convergence of forward-backward accelerated algorithms without knowledge of the modulus of strong convexity

A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method. This forward-backward technique has been further advanced with the introduction of its proximal generalization, commonly known as the fast iterative shrinkage-thresholding algorithm (FISTA), which enjoys widespread application in image science and engineering. Nonetheless, it remains unclear whether both NAG and FISTA exhibit linear convergence for strongly convex functions. Remarkably, these algorithms demonstrate convergence without requiring any prior knowledge of strongly convex modulus, and this intriguing characteristic has been acknowledged as an open problem in the comprehensive review [Chambolle and Pock, 2016, Appendix B]. In this paper, we address this question by utilizing the high-resolution ordinary differential equation (ODE) framework. Expanding upon the established phase-space representation, we emphasize the distinctive approach employed in crafting the Lyapunov function, which involves a dynamically adapting coefficient of kinetic energy that evolves throughout the iterations. Furthermore, we highlight that the linear convergence of both NAG and FISTA is independent of the parameter $r$. Additionally, we demonstrate that the square of the proximal subgradient norm likewise advances towards linear convergence.

math.OC↗