Author name cluster

Mingyang Chen

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.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video

Renlong Wu
Zhilu Zhang
Mingyang Chen
Zifei Yan
Wangmeng Zuo

Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when using such videos for reconstructing 4D models. Although a few approaches attempted to address the problem, they struggled to produce high-quality results, due to the inaccuracy in estimating continuous dynamic representations within the exposure time. Encouraged by recent works in 3D motion trajectory modeling using 3D Gaussian Splatting (3DGS), we take 3DGS as the scene representation manner, and propose Deblur4DGS to obtain a high-quality 4D model from blurry monocular video. Specifically, we transform continuous dynamic representations estimation within an exposure time into the exposure time estimation. Moreover, we introduce the exposure regularization term, multi-frame, and multi-resolution consistency regularization term to avoid trivial solutions. Furthermore, to better represent objects with large motion, we suggest blur-aware variable canonical Gaussians. Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives, including deblurring, frame interpolation, and video stabilization. Extensive experiments in both synthetic and real-world data on the above four tasks show that Deblur4DGS outperforms state-of-the-art 4D reconstruction methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection

Mingyang Chen
Jiawei Du
Bo Huang
Yi Wang
Xiaobo Zhang
Wei Wang

Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. This omission may hinder the constructed subset from capturing subtle yet critical distributional structures that underpin effective model training. In this work, we propose a novel, theoretically grounded approach that leverages diffusion models to estimate data likelihood via reconstruction deviation induced by partial reverse denoising. Specifically, we establish a formal connection between reconstruction error and data likelihood, grounded in the Evidence Lower Bound (ELBO) of Markovian diffusion processes, thereby enabling a principled, distribution-aware scoring criterion for data selection. Complementarily, we introduce an efficient information-theoretic method to identify the optimal reconstruction timestep, ensuring that the deviation provides a reliable signal indicative of underlying data likelihood. Extensive experiments on ImageNet demonstrate that reconstruction deviation offers an effective scoring criterion, consistently outperforming existing baselines across selection ratios, and closely matching full-data training using only 50% of the data. Further analysis shows that the likelihood-informed nature of our score reveals informative insights in data selection, shedding light on the interplay between data distributional characteristics and model learning preferences.

PDF Details DOI

AAAI Conference 2026 Conference Paper

UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction

Zhiqiang Liu
Yin Hua
Mingyang Chen
Yichi Zhang
Zhuo Chen
Lei Liang
Wen Zhang

Real-world knowledge graphs (KGs) contain not only standard triple-based facts, but also more complex, heterogeneous types of facts, such as hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts that imply relationships between facts. These richer forms of representation have attracted significant attention due to their enhanced expressiveness and capacity to model complex semantics in real-world scenarios. However, most existing studies suffer from two main limitations: (1) they typically focus on modeling only specific types of facts, thus making it difficult to generalize to real-world scenarios with multiple fact types; and (2) they struggle to achieve generalizable hierarchical (inter-fact and intra-fact) modeling due to the complexity of these representations. To overcome these limitations, we propose UniHR, a Unified Hierarchical Representation learning framework, which consists of a learning-optimized Hierarchical Data Representation (HiDR) module and a unified Hierarchical Structure Learning (HiSL) module. The HiDR module unifies hyper-relational KGs, temporal KGs, and nested factual KGs into triple-based representations. Then HiSL incorporates intra-fact and inter-fact message passing, focusing on enhancing both semantic information within individual facts and enriching the structural information between facts. To go beyond the unified method itself, we further explore the potential of unified representation in complex real-world scenarios. Extensive experiments on 9 datasets across 5 types of KGs demonstrate the effectiveness of UniHR and highlight the strong potential of unified representations.

PDF Details DOI

EAAI Journal 2025 Journal Article

A knowledge-guided reinforcement learning method for lateral path tracking

Bo Hu
Sunan Zhang
Yuxiang Feng
Bingbing Li
Hao Sun
Mingyang Chen
Weichao Zhuang
Yi Zhang

Lateral Control algorithms in autonomous vehicles often necessitates an online fine-tuning procedure in the real world. While reinforcement learning (RL) enables vehicles to learn and improve the lateral control performance through repeated trial and error interactions with a dynamic environment, applying RL directly to safety-critical applications in real physical world is challenging because ensuring safety during the learning process remains difficult. To enable safe learning, a promising direction is to make use of previously gathered offline data, which is frequently accessible in engineering applications. In this context, this paper presents a set of knowledge-guided RL algorithms that can not only fully leverage the prior collected offline data without the need of a physics-based simulator, but also allow further online policy improvement in a smooth, safe and efficient manner. To evaluate the effectiveness of the proposed algorithms on a real controller, a hardware-in-the-loop and a miniature vehicle platform are built. Compared with the vanilla RL, behavior cloning and the existing controller, the proposed algorithms realize a closed-loop solution for lateral control problems from offline training to online fine-tuning, making it attractive for future similar RL-based controller to build upon.

Details DOI

ICLR Conference 2025 Conference Paper

Influence-Guided Diffusion for Dataset Distillation

Mingyang Chen
Jiawei Du
Bo Huang 0017
Yi Wang 0017
Xiaobo Zhang
Wei Wang 0011

Dataset distillation aims to streamline the training process by creating a compact yet effective dataset for a much larger original dataset. However, existing methods often struggle with distilling large, high-resolution datasets due to prohibitive resource costs and limited performance, primarily stemming from sample-wise optimizations in the pixel space. Motivated by the remarkable capabilities of diffusion generative models in learning target dataset distributions and controllably sampling high-quality data tailored to user needs, we propose framing dataset distillation as a controlled diffusion generation task aimed at generating data specifically tailored for effective training purposes. By establishing a correlation between the overarching objective of dataset distillation and the trajectory influence function, we introduce the Influence-Guided Diffusion (IGD) sampling framework to generate training-effective data without the need to retrain diffusion models. An efficient guided function is designed by leveraging the trajectory influence function as an indicator to steer diffusions to produce data with influence promotion and diversity enhancement. Extensive experiments show that the training performance of distilled datasets generated by diffusions can be significantly improved by integrating with our IGD method and achieving state-of-the-art performance in distilling ImageNet datasets. Particularly, an exceptional result is achieved on the ImageNet-1K, reaching 60.3\% at IPC=50. Our code is available at https://github.com/mchen725/DD_IGD.

Details

NeurIPS Conference 2025 Conference Paper

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Mingyang Chen
Linzhuang Sun
Tianpeng Li
Haoze Sun
Chenzheng Zhu
Haofen Wang
Jeff Pan
Wen Zhang

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2. 5-7B(-Instruct) and Qwen2. 5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.

PDF Details

AIIM Journal 2024 Journal Article

Abnormal recognition-assisted and onset-offset aware network for pathological wearable ECG delineation

Yue Zhang
Jiewei Lai
Chenyu Zhao
Jinliang Wang
Yong Yan
Mingyang Chen
Lei Ji
Jun Guo

Electrocardiogram (ECG) delineation is essential to the identification of abnormal cardiac status, especially when ECG signals are remotely monitored with wearable devices. The complexity and diversity of cardiac conditions generate numerous pathological ECG patterns, not only requiring the recognition of normal ECG but also addressing an extensive range of abnormal ECG patterns, posing a challenging task. Therefore, we propose an abnormal recognition-assisted network to integrate supplementary information on diverse ECG patterns. Simultaneously, we design an onset-offset aware loss to enhance precise waveform localization. Specifically, we establish a two-branch framework where ECG delineation serves as the target task, producing the final segmentation results. Additionally, the abnormal recognition-assisted network serves as an auxiliary task, extracting multi-label pathological information from ECGs. This joint learning approach establishes crucial correlations between ECG delineation and associated ECG abnormalities. The correlations enable the model to demonstrate sufficient generalization in the presence of diverse abnormal ECG patterns. Besides, onset-offset aware loss focuses intensively on wave onsets and offsets by applying biased weights to various waveform positions. This approach ensures a focus on precise localization, facilitating seamless integration into cross-entropy loss function. A large-scale wearable 12-lead dataset containing 4, 913 signals is collected, offering an extensive range of ECG data for model training. Results demonstrate that our method achieves outstanding performance on two test datasets, attaining sensitivity of 94. 97% and 94. 27% and an error tolerance lower than 20 ms. Furthermore, our method is effective for various aberrant ECG signals, including ST-segment changes, atrial premature beats, and right and left bundle branch blocks.

Details DOI

AIIM Journal 2024 Journal Article

Deep learning algorithms for melanoma detection using dermoscopic images: A systematic review and meta-analysis

Zichen Ye
Daqian Zhang
Yuankai Zhao
Mingyang Chen
Huike Wang
Samuel Seery
Yimin Qu
Peng Xue

Background Melanoma is a serious risk to human health and early identification is vital for treatment success. Deep learning (DL) has the potential to detect cancer using imaging technologies and many studies provide evidence that DL algorithms can achieve high accuracy in melanoma diagnostics. Objectives To critically assess different DL performances in diagnosing melanoma using dermatoscopic images and discuss the relationship between dermatologists and DL. Methods Ovid-Medline, Embase, IEEE Xplore, and the Cochrane Library were systematically searched from inception until 7th December 2021. Studies that reported diagnostic DL model performances in detecting melanoma using dermatoscopic images were included if they had specific outcomes and histopathologic confirmation. Binary diagnostic accuracy data and contingency tables were extracted to analyze outcomes of interest, which included sensitivity (SEN), specificity (SPE), and area under the curve (AUC). Subgroup analyses were performed according to human-machine comparison and cooperation. The study was registered in PROSPERO, CRD42022367824. Results 2309 records were initially retrieved, of which 37 studies met our inclusion criteria, and 27 provided sufficient data for meta-analytical synthesis. The pooled SEN was 82 % (range 77–86), SPE was 87 % (range 84–90), with an AUC of 0. 92 (range 0. 89–0. 94). Human-machine comparison had pooled AUCs of 0. 87 (0. 84–0. 90) and 0. 83 (0. 79–0. 86) for DL and dermatologists, respectively. Pooled AUCs were 0. 90 (0. 87–0. 93), 0. 80 (0. 76–0. 83), and 0. 88 (0. 85–0. 91) for DL, and junior and senior dermatologists, respectively. Analyses of human-machine cooperation were 0. 88 (0. 85–0. 91) for DL, 0. 76 (0. 72–0. 79) for unassisted, and 0. 87 (0. 84–0. 90) for DL-assisted dermatologists. Conclusions Evidence suggests that DL algorithms are as accurate as senior dermatologists in melanoma diagnostics. Therefore, DL could be used to support dermatologists in diagnostic decision-making. Although, further high-quality, large-scale multicenter studies are required to address the specific challenges associated with medical AI-based diagnostics.

Details DOI

NeurIPS Conference 2024 Conference Paper

DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis

Shangshang Yang
Mingyang Chen
Ziwen Wang
Xiaoshan Yu
Panpan Zhang
Haiping Ma
Xingyi Zhang

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the interaction-agnostic exercise and concept representations be learned poorly, failing to provide high robustness against noise in students' interactions. Besides, lower-order exercise latent representations obtained in shallow layers are not well explored when learning the student representation. To tackle the issues, this paper suggests a meta multigraph-assisted disentangled graph learning framework for CD (DisenGCD), which learns three types of representations on three disentangled graphs: student-exercise-concept interaction, exercise-concept relation, and concept dependency graphs, respectively. Specifically, the latter two graphs are first disentangled from the interaction graph. Then, the student representation is learned from the interaction graph by a devised meta multigraph learning module; multiple learnable propagation paths in this module enable current student latent representation to access lower-order exercise latent representations, which can lead to more effective nad robust student representations learned; the exercise and concept representations are learned on the relation and dependency graphs by graph attention modules. Finally, a novel diagnostic function is devised to handle three disentangled representations for prediction. Experiments show better performance and robustness of DisenGCD than state-of-the-art CD methods and demonstrate the effectiveness of the disentangled learning framework and meta multigraph module. The source code is available at https: //github. com/BIMK/Intelligent-Education/tree/main/DisenGCD.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Analogical Inference Enhanced Knowledge Graph Embedding

Zhen Yao
Wen Zhang
Mingyang Chen
Yufeng Huang
Yi Yang
Huajun Chen

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding

Mingyang Chen
Wen Zhang
Zhen Yao
Yushan Zhu
Yang Gao
Jeff Z. Pan
Huajun Chen

We propose an entity-agnostic representation learning method for handling the problem of inefficient parameter storage costs brought by embedding knowledge graphs. Conventional knowledge graph embedding methods map elements in a knowledge graph, including entities and relations, into continuous vector spaces by assigning them one or multiple specific embeddings (i.e., vector representations). Thus the number of embedding parameters increases linearly as the growth of knowledge graphs. In our proposed model, Entity-Agnostic Representation Learning (EARL), we only learn the embeddings for a small set of entities and refer to them as reserved entities. To obtain the embeddings for the full set of entities, we encode their distinguishable information from their connected relations, k-nearest reserved entities, and multi-hop neighbors. We learn universal and entity-agnostic encoders for transforming distinguishable information into entity embeddings. This approach allows our proposed EARL to have a static, efficient, and lower parameter count than conventional knowledge graph embedding methods. Experimental results show that EARL uses fewer parameters and performs better on link prediction tasks than baselines, reflecting its parameter efficiency.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

Mingyang Chen
Wen Zhang
Yuxia Geng
Zezhong Xu
Jeff Z. Pan
Huajun Chen

Knowledge graphs (KGs) have become valuable knowledge resources in various applications, and knowledge graph embedding (KGE) methods have garnered increasing attention in recent years. However, conventional KGE methods still face challenges when it comes to handling unseen entities or relations during model testing. To address this issue, much effort has been devoted to various fields of KGs. In this paper, we use a set of general terminologies to unify these methods and refer to them collectively as Knowledge Extrapolation. We comprehensively summarize these methods, classified by our proposed taxonomy, and describe their interrelationships. Additionally, we introduce benchmarks and provide comparisons of these methods based on aspects that are not captured by the taxonomy. Finally, we suggest potential directions for future research.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting

Mingyang Chen
Wen Zhang
Zhen Yao
Xiangnan Chen
Mengxiao Ding
Fei Huang
Huajun Chen

We study the knowledge extrapolation problem to embed new components (i. e. , entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed an emerging KG with unseen entities and relations. To solve this problem, we introduce the meta-learning setting, where a set of tasks are sampled on the existing KG to mimic the link prediction task on the emerging KG. Based on sampled tasks, we meta-train a graph neural network framework that can construct features for unseen components based on structural information and output embeddings for them. Experimental results show that our proposed method can effectively embed unseen components and outperforms models that consider inductive settings for KGs and baselines that directly use conventional KG embedding methods.

PDF Details DOI