Author name cluster

Mingcai 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.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models

Yifan Jia
Yuntao Du
Kailin Jiang
Yuyang Liang
Qihan Ren
Yi Xin
Rui Yang
Fenze Feng

Large Multimodal Models (LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation (RAG) frameworks, where the contextual information from external sources may contradict the model’s internal parametric knowledge, leading to unreliable outputs. However, existing benchmarks fail to reflect such realistic conflict scenarios. Most focus solely on intra-memory conflicts, while context-memory and inter-context conflicts remain largely unaddressed. Furthermore, commonly used factual knowledge-based evaluations are often overlooked, and existing datasets lack a thorough investigation into conflict detection capabilities.To bridge this gap, we propose MMKC-Bench, a benchmark designed to evaluate factual knowledge conflicts in both context-memory and inter-context scenarios. MMKC-Bench encompasses four types of multimodal knowledge conflicts and includes 1,881 knowledge instances and 3,997 images across 32 broad types, collected through automated pipelines with human verification. We evaluate four representative series of LMMs on both model behavior analysis and conflict detection tasks. Our findings show that while current LMMs are capable of recognizing knowledge conflicts, they tend to favor internal parametric knowledge over external evidence. We hope MMKC-Bench will foster further research in multimodal knowledge conflict and enhance the development of multimodal RAG systems.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Normalize Then Propagate: Efficient Homophilous Regularization for Few-Shot Semi-Supervised Node Classification

Baoming Zhang
MingCai Chen
Jianqing Song
Shuangjie Li
Jie Zhang
Chongjun Wang

Graph Neural Networks (GNNs) have demonstrated remarkable ability in semi-supervised node classification. However, most existing GNNs rely heavily on a large amount of labeled data for training, which is labor-intensive and requires extensive domain knowledge. In this paper, we first analyze the restrictions of GNNs generalization from the perspective of supervision signals in the context of few-shot semi-supervised node classification. To address these challenges, we propose a novel algorithm named NormProp, which utilizes the homophily assumption of unlabeled nodes to generate additional supervision signals, thereby enhancing the generalization against label scarcity. The key idea is to efficiently capture both the class information and the consistency of aggregation during message passing, via decoupling the direction and Euclidean norm of node representations. Moreover, we conduct a theoretical analysis to determine the upper bound of Euclidean norm, and then propose homophilous regularization to constraint the consistency of unlabeled nodes. Extensive experiments demonstrate that NormProp achieve state-of-the-art performance under low-label rate scenarios with low computational complexity.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Robust Logit Adjustment for Learning with Long-Tailed Noisy Data

MingCai Chen
Yuntao Du
Wenyu Jiang
Baoming Zhang
Shuai Feng
Yi Xin
Chongjun Wang

Learning with noisy labels (LNL) methods have enabled the deployment of machine learning systems with imperfectly labeled data. However, these methods often struggle to identify noise in the presence of long-tailed (LT) class distributions, where the memorization effect becomes class-dependent. Conversely, LT methods are suboptimal under label noise, as it hinders access to accurate label frequency statistics. This study aims to address the long-tailed noisy data by bridging the methodological gap between LNL and LT approaches. We propose a direct solution, termed Robust Logit Adjustment, which estimates ground-truth labels through label refurbishment, thereby mitigating the impact of label noise. Simultaneously, our method incorporates the distribution of training-time corrected target labels into the LT method logit adjustment, providing class-rebalanced supervision. Extensive experiments on both synthetic and real-world long-tailed noisy datasets demonstrate the superior performance of our method.

PDF Details DOI

ICML Conference 2025 Conference Paper

Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data

Mingcai Chen
Baoming Zhang
Zongbo Han
Wenyu Jiang
Yanmeng Wang
Shuai Feng
Yuntao Du 0001
Bingkun Bao

Modern machine learning applications are characterized by the increasing size of deep models and the growing diversity of data modalities. This trend underscores the importance of efficiently adapting pre-trained multi-modal models to the test distribution in real time, i. e. , multi-modal test-time adaptation. In practice, the magnitudes of multi-modal shifts vary because multiple data sources interact with the impact factor in diverse manners. In this research, we investigate the the under-explored practical scenario uni-modal distribution shift, where the distribution shift influences only one modality, leaving the others unchanged. Through theoretical and empirical analyses, we demonstrate that the presence of such shift impedes multi-modal fusion and leads to the negative transfer phenomenon in existing test-time adaptation techniques. To flexibly combat this unique shift, we propose a selective adaptation schema that incorporates multiple modality-specific adapters to accommodate potential shifts and a “router” module that determines which modality requires adaptation. Finally, we validate the effectiveness of our proposed method through extensive experimental evaluations. Code available at https: //github. com/chenmc1996/Uni-Modal-Distribution-Shift.

Details

ICLR Conference 2024 Conference Paper

DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

Wenyu Jiang
Hao Cheng 0014
Mingcai Chen
Chongjun Wang
Hongxin Wei

Modern neural networks are known to give overconfident predictions for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and recent studies emphasize the role of uncertainty in designing the sampling strategy for outlier datasets. However, the OOD samples selected solely based on predictive uncertainty can be biased towards certain types, which may fail to capture the full outlier distribution. In this work, we empirically show that diversity is critical in sampling outliers for OOD detection performance. Motivated by the observation, we propose a straightforward and novel sampling strategy named DOS (Diverse Outlier Sampling) to select diverse and informative outliers. Specifically, we cluster the normalized features at each iteration, and the most informative outlier from each cluster is selected for model training with absent category loss. With DOS, the sampled outliers efficiently shape a globally compact decision boundary between ID and OOD data. Extensive experiments demonstrate the superiority of DOS, reducing the average FPR95 by up to 25.79% on CIFAR-100 with TI-300K.

Details

NeurIPS Conference 2024 Conference Paper

V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark

Yi Xin
Siqi Luo
Xuyang Liu
Yuntao Du
Haodi Zhou
Xinyu Cheng
Christina Lee
Junlong Du

Parameter-efficient transfer learning (PETL) methods show promise in adapting a pre-trained model to various downstream tasks while training only a few parameters. In the computer vision (CV) domain, numerous PETL algorithms have been proposed, but their direct employment or comparison remains inconvenient. To address this challenge, we construct a Unified Visual PETL Benchmark (V-PETL Bench) for the CV domain by selecting 30 diverse, challenging, and comprehensive datasets from image recognition, video action recognition, and dense prediction tasks. On these datasets, we systematically evaluate 25 dominant PETL algorithms and open-source a modular and extensible codebase for fair evaluation of these algorithms. V-PETL Bench runs on NVIDIA A800 GPUs and requires approximately 310 GPU days. We release all the benchmark, making it more efficient and friendly to researchers. Additionally, V-PETL Bench will be continuously updated for new PETL algorithms and CV tasks.

PDF Details DOI

ECAI Conference 2023 Conference Paper

A Flexible Debiasing Framework for Fair Heterogeneous Information Network Embedding

Meng Cao 0004
Mingcai Chen
Jianqing Song
Chen-Xuan Fang
Chongjun Wang

Heterogeneous Information Networks (HINs) are prevalent in real-world systems. Recent advances in network embedding provide an effective way of encoding HINs into low-dimensional vectors. However, there is a growing concern that existing HIN embedding algorithms may suffer from the problem of generating biased representations, resulting in discrimination against certain demographic groups. In this paper, we propose a flexible debiasing framework for fair HIN embedding to address this issue. Specifically, we first formalize measurements and the definition of fairness in HIN embedding. Then, we propose a debiasing framework named FairHGNN, including a novel meta-path sampling method that focuses on mitigating the bias in random walks, and a fairness constraint with Wasserstein distance to alleviate the algorithmic bias in Graph Neural Networks (GNNs). Experimental results on real-world datasets validate the efficacy of FairHGNN in promoting fairness and maintaining good utility.

Details

IJCAI Conference 2023 Conference Paper

A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification

MingCai Chen
Yu Zhao
Zhonghuang Wang
Bing He
Jianhua Yao

Immune repertoire classification, a typical multiple instance learning (MIL) problem, is a frontier research topic in computational biology that makes transformative contributions to new vaccines and immune therapies. However, the traditional instance-space MIL, directly assigning bag-level labels to instances, suffers from the massive amount of noisy labels and extremely low witness rate. In this work, we propose a noisy-label-learning formulation to solve the immune repertoire classification task. To remedy the inaccurate supervision of repertoire-level labels for a sequence-level classifier, we design a robust training strategy: The initial labels are smoothed to be asymmetric and are progressively corrected using the model's predictions throughout the training process. Furthermore, two models with the same architecture but different parameter initialization are co-trained simultaneously to remedy the known ``confirmation bias'' problem in the self-training-like schema. As a result, we obtain accurate sequence-level classification and, subsequently, repertoire-level classification. Experiments on the Cytomegalovirus (CMV) and Cancer datasets demonstrate our method's effectiveness and superior performance on sequence-level and repertoire-level tasks. Code available at https: //github. com/TencentAILabHealthcare/NLL-IRC.

PDF Details DOI

TMLR Journal 2023 Journal Article

Bidirectional View based Consistency Regularization for Semi-Supervised Domain Adaptation

Yuntao Du
娟江
Hongtao Luo
Haiyang Yang
MingCai Chen
Chongjun Wang

Distinguished from unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA) could access a few labeled target samples during learning additionally. Although achieving remarkable progress, target supervised information is easily overwhelmed by massive source supervised information, as there are many more labeled source samples than those in the target domain. In this work, we propose a novel method BVCR that better utilizes the supervised information by three schemes, i.e., modeling, exploration, and interaction. In the modeling scheme, BVCR models the source supervision and target supervision separately to avoid target supervised information being overwhelmed by source supervised information and better utilize the target supervision. Besides, as both supervised information naturally offer distinct views for the target domain, the exploration scheme performs intra-domain consistency regularization to better explore target information with bidirectional views. Moreover, as both views are complementary to each other, the interaction scheme introduces inter-domain consistency regularization to activate information interaction bidirectionally. Thus, the proposed method is elegantly symmetrical by design and easy to implement. Extensive experiments are conducted, and the results show the effectiveness of the proposed method.

PDF Details

AAAI Conference 2023 Conference Paper

READ: Aggregating Reconstruction Error into Out-of-Distribution Detection

Wenyu Jiang
Yuxin Ge
Hao Cheng
MingCai Chen
Shuai Feng
Chongjun Wang

Detecting out-of-distribution (OOD) samples is crucial to the safe deployment of a classifier in the real world. However, deep neural networks are known to be overconfident for abnormal data. Existing works directly design score function by mining the inconsistency from classifier for in-distribution (ID) and OOD. In this paper, we further complement this inconsistency with reconstruction error, based on the assumption that an autoencoder trained on ID data cannot reconstruct OOD as well as ID. We propose a novel method, READ (Reconstruction Error Aggregated Detector), to unify inconsistencies from classifier and autoencoder. Specifically, the reconstruction error of raw pixels is transformed to latent space of classifier. We show that the transformed reconstruction error bridges the semantic gap and inherits detection performance from the original. Moreover, we propose an adjustment strategy to alleviate the overconfidence problem of autoencoder according to a fine-grained characterization of OOD data. Under two scenarios of pre-training and retraining, we respectively present two variants of our method, namely READ-MD (Mahalanobis Distance) only based on pre-trained classifier and READ-ED (Euclidean Distance) which retrains the classifier. Our methods do not require access to test time OOD data for fine-tuning hyperparameters. Finally, we demonstrate the effectiveness of the proposed methods through extensive comparisons with state-of-the-art OOD detection algorithms. On a CIFAR-10 pre-trained WideResNet, our method reduces the average FPR@95TPR by up to 9.8% compared with previous state-of-the-art.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise

MingCai Chen
Hao Cheng
Yuntao Du
Ming Xu
Wenyu Jiang
Chongjun Wang

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the errors accumulate. To sufficiently exploit information from noisy labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR)—a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art performance across datasets and noise types, namely CIFAR under different levels of synthetic noise and mini-WebVision and ANIMAL-10N with real-world noise.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Semi-supervised Learning with Multi-Head Co-Training

MingCai Chen
Yuntao Du
Yi Zhang
Shuwei Qian
Chongjun Wang

Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. Without natural split of features, single-view co-training works at the cost of training extra classifiers, where the algorithm should be delicately designed to prevent individual classifiers from collapsing into each other. To remove these obstacles which deter the adoption of single-view co-training, we present a simple and efficient algorithm Multi-Head Co-Training. By integrating base learners into a multi-head structure, the model is in a minimal amount of extra parameters. Every classification head in the unified model interacts with its peers through a “Weak and Strong Augmentation” strategy, in which the diversity is naturally brought by the strong data augmentation. Therefore, the proposed method facilitates single-view co-training by 1). promoting diversity implicitly and 2). only requiring a small extra computational overhead. The effectiveness of Multi- Head Co-Training is demonstrated in an empirical study on standard semi-supervised learning benchmarks.

PDF Details