Author name cluster

Xiang Wei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

EAAI Journal 2026 Journal Article

Number-agnostic decoupled class discovery for open-world semi-supervised learning

Guanjia Zhang
Weiwei Xing
Xiaoyu Guo
Yue Cheng
Xiang Wei
Zhengyang Zhao

Open-world semi-supervised learning aims to discriminate known and novel classes in unlabeled data within a semi-supervised learning paradigm. Except for a few methods, many clustering-based open-world semi-supervised learning methods rely on a predefined number of classes to recognize novel classes, which hampers the ability of the model to discover novel classes and decreases the generalization performance. Furthermore, the coupled training of supervised and unsupervised learning on a shared classifier accelerates the learning of labeled known classes, inevitably satisfying the supervised objective faster and leading to biased predictions. To address these challenges in open-world environments, we propose a number-agnostic decoupled class discovery approach, named NADCD. In NADCD, a semi-supervised information propagation clustering algorithm is proposed to adaptively estimate the number of classes and dynamically generate class prototypes. These prototypes are subsequently employed to facilitate the learning of discriminative representations across different samples. In addition, NADCD decouples the supervised and unsupervised training objectives by introducing an auxiliary bias-decoupling classifier on the representation encoder, thereby mitigating the bias inherent in the learned representations of novel classes. Extensive experimental results across different settings on three benchmark datasets demonstrate the effectiveness of NADCD. We will release the code at: https: //github. com/srxhlife/NADCD.

Details DOI

AAAI Conference 2026 Conference Paper

Sampling Control for Imbalanced Calibration in Semi-Supervised Learning

Senmao Tian
Xiang Wei
Shunli Zhang

Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classification. Although existing methods address this issue by adjusting logits based on the estimated class distribution of unlabeled data, they often handle model imbalance in a coarse-grained manner, conflating data imbalance with bias arising from varying class-specific learning difficulties. To address this issue, we propose a unified framework, SC-SSL, which suppresses model bias through decoupled sampling control. During training, we identify the key variables for sampling control under ideal conditions. By introducing a classifier with explicit expansion capability and adaptively adjusting sampling probabilities across different data distributions, SC-SSL mitigates feature-level imbalance for minority classes. In the inference phase, we further analyze the weight imbalance of the linear classifier and apply post-hoc sampling control with an optimization bias vector to directly calibrate the logits. Extensive experiments across various benchmark datasets and distribution settings validate the consistency and state-of-the-art performance of SC-SSL.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

APIMig: A Project-Level Cross-Multi-Version API Migration Framework Based on Evolution Knowledge Graph

Li Kuang
Qi Xie
Haiyang Yang
Yang Yang
Xiang Wei
HaoYue Kang
Yingjie Xia

API migration is essential for software maintenance due to the rapid evolution of third-party libraries where API elements may change continuously through updates. There are two main challenges for API migration at the project level, especially across multiple versions: 1) lack of specific library evolution knowledge across multi-version; 2) difficulty in identifying the chain of changes at the project level. This paper proposes a project-level cross-multi-version API migration framework APIMig. We first construct an API evolution knowledge graph (KG) to capture changes between adjacent library versions and then derive coherent cross-version API evolution knowledge by KG reasoning. Second, we design a chain exploration algorithm to track the chain of changes and aggregate the affected code segments. Finally, a large language model is employed in completing API migration by providing the API evolution knowledge and the chain of changes. We construct an evolution KG for the Lucene library from version 4. 0. 0 to 10. 1. 0 and evaluate our approach through project migration pairs that depend on different major versions. Our framework shows improvements over the baseline in migrating projects across 7 major versions, achieving average increases of 16. 52% in CodeBLEU scores and 28. 49% in VCEU scores in GPT-4o.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel

Alan J. X. Guo
Sihan Sun
Xiang Wei
Mengyi Wei
Xin Chen

With the emergence of new storage and communication methods, the insertion, deletion, and substitution (IDS) channel has attracted considerable attention. However, many topics on the IDS channel and the associated Levenshtein distance remain open, making the invention of a novel IDS-correcting code a hard task. Furthermore, current studies on single-IDS-correcting code misalign with the requirements of applications which necessitates the correcting of multiple errors. Compromise solutions have involved shortening codewords to reduce the chance of multiple errors. However, the code rates of existing codes are poor at short lengths, diminishing the overall storage density. In this study, a novel method is introduced for designing high-code-rate single-IDS-correcting codewords through deep Levenshtein distance embedding. A deep learning model is utilized to project the sequences into embedding vectors that preserve the Levenshtein distances between the original sequences. This embedding space serves as a proxy for the complex Levenshtein domain, within which algorithms for codeword search and segment correcting is developed. While the concept underpinning this approach is straightforward, it bypasses the mathematical challenges typically encountered in code design. The proposed method results in a code rate that outperforms existing combinatorial solutions, particularly for designing short-length codewords.

PDF Details

NeurIPS Conference 2025 Conference Paper

HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses

Zhichao Deng
Zhikun Liu
Junxue Wang
Shengqian Chen
Xiang Wei
Qiang Yu

Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient framework for temporal information processing. However, existing studies overlook a fundamental property widely observed in biological neurons—synaptic heterogeneity, which plays a crucial role in temporal processing and cognitive capabilities. To bridge this gap, we introduce HetSyn, a generalized framework that models synaptic heterogeneity with synapse-specific time constants. This design shifts temporal integration from the membrane potential to the synaptic current, enabling versatile timescale integration and allowing the model to capture diverse synaptic dynamics. We implement HetSyn as HetSynLIF, an extended form of the leaky integrate-and-fire (LIF) model equipped with synapse-specific decay dynamics. By adjusting the parameter configuration, HetSynLIF can be specialized into vanilla LIF neurons, neurons with threshold adaptation, and neuron-level heterogeneous models. We demonstrate that HetSynLIF not only improves the performance of SNNs across a variety of tasks—including pattern generation, delayed match-to-sample, speech recognition, and visual recognition—but also exhibits strong robustness to noise, enhanced working memory performance, efficiency under limited neuron resources, and generalization across timescales. In addition, analysis of the learned synaptic time constants reveals trends consistent with empirical observations in biological synapses. These findings underscore the significance of synaptic heterogeneity in enabling efficient neural computation, offering new insights into brain-inspired temporal modeling. Code available at: https: //github. com/dzcgood/HetSyn.

PDF Details

AAAI Conference 2025 Conference Paper

LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing

Weiwei Xing
Yue Cheng
Hongzhu Yi
Xiaohui Gao
Xiang Wei
Xiaoyu Guo
Yumin Zhang
Xinyu Pang

Classifiers often learn to be biased corresponding to the class-imbalanced dataset under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a class-irrelevant image's logit, we further utilize a cheaper form of consistency gradients, which can be widely applicable to various class-imbalanced SSL (CISSL) models. We theoretically analyze that the process of refining pseudo-labels with a baseline image (solid color image without any patterns) in the basic SSL algorithm implicitly utilizes integrated gradient flow training, which can improve the attribution ability. Based on the analysis, we propose a consistently conflicting gradient-based debiasing scheme dubbed LCGC, by encouraging biased class predictions during training. We intentionally update the pseudo-labels whose gradient conflicts with the debiased logits, which is represented as the optimization direction offered by the over-imbalanced classifier predictions. Then, we debias the predictions by subtraction the baseline image logits during testing. Extensive experiments demonstrate that our method can significantly improve the prediction accuracy of existing CISSL models on public benchmarks.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Levenshtein Distance Embedding with Poisson Regression for DNA Storage

Xiang Wei
Alan J.X. Guo
Sihan Sun
Mengyi Wei
Wei Yu

Efficient computation or approximation of Levenshtein distance, a widely-used metric for evaluating sequence similarity, has attracted significant attention with the emergence of DNA storage and other biological applications. Sequence embedding, which maps Levenshtein distance to a conventional distance between embedding vectors, has emerged as a promising solution. In this paper, a novel neural network-based sequence embedding technique using Poisson regression is proposed. We first provide a theoretical analysis of the impact of embedding dimension on model performance and present a criterion for selecting an appropriate embedding dimension. Under this embedding dimension, the Poisson regression is introduced by assuming the Levenshtein distance between sequences of fixed length following a Poisson distribution, which naturally aligns with the definition of Levenshtein distance. Moreover, from the perspective of the distribution of embedding distances, Poisson regression approximates the negative log likelihood of the chi-squared distribution and offers advancements in removing the skewness. Through comprehensive experiments on real DNA storage data, we demonstrate the superior performance of the proposed method compared to state-of-the-art approaches.

PDF Details DOI

ICRA Conference 2014 Conference Paper

Development of a symmetrical spiral wireless microrobot in pipe for biomedical applications

Shuxiang Guo
Xiang Wei
Jian Guo 0003
Wei Wei
Yuehui Ji
Yunliang Wang

Colonoscopy is an important procedure for the diagnosis of various pathologies, in particular cancer of the colon and of the rectum. However, colonoscopy is a procedure often painful for the patient and complex for the doctor. So in the biomedical field, a wireless microrobot in pipe that can move smoothly in water or aqueous medium has urgently been demanded. In this paper, we developed a new kind of wireless microrobot with symmetrical spiral structure, which also had symmetrical kinematic characteristics. According to the hydromechanical lubrication theory and Newton viscous law, we build the motion model of the microrobot, which will provide a theoretical basis on designing the optimal structure parameters of the microrobot. Through analysis, simulations and experiments, this paper had evaluated the effect of spiral angle, which could realize forward-backward, upward-downward motion and stopping at any position we need in the pipe. In addition, we obtained the moving speeds of forward-backward and upward-downward motion in the pipe. The experimental results indicated that the maximum moving speed is 36. 5 mm/s at 14 Hz in the horizontal direction and 4. 6 mm/s at 16Hz in the vertical direction with input currents of 0. 7A. Finally, we designed a control panel for this system, which can control the microrobot current motion states intuitively and easily, and make our system more portable and compact. The developed wireless microrobot can move smoothly in water and other liquid medium and is very useful in the industrial.

Details