Author name cluster

Chuanbin Liu

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.

7 papers

1 author row

EAAI Journal 2026 Journal Article

A case-based reasoning-driven clustering imputation and noise-resistant classification learning paradigm for financial distress prediction with missing and noisy data

Mengxin Li
Lean Yu
Chuanbin Liu

Data missing and noise problems are often encountered when predicting financial distress in real-world scenarios. To address and eliminate the negative effects of missing and noisy data, a novel case-based reasoning CBR-driven clustering imputation and noise-resistant ClusImpute-NoisRes classification learning paradigm is proposed for financial distress prediction to achieve excellent imputation and prediction performance. In this learning paradigm, CBR-driven clustering imputation and CBR-driven noise-resistant classifier prediction are two primary stages. In the first stage, a clustering-based hybrid CBR-driven weighted ClusHyCBR imputation method is introduced to handle the issue of missing data and their uneven distribution. In the second stage, a CBR-driven noise-resistant classification model is constructed to identify class noise and reduce the negative interference of class noise on the prediction model. For illustration and verification, a dataset of Chinese-listed enterprises and its derived multiple datasets with different missing degrees and noise levels are used to conduct the experimental study. Experimental results demonstrate that the proposed ClusHyCBR imputation method consistently outperforms competing methods, improving Type II accuracy by 1.92 percent to 8.99 percent on the original dataset, with increasingly larger gains on higher missing degrees. The proposed CBR-driven noise-resistant classification model maintains noise identification accuracy above 0.8722 and Type II accuracy above 0.7022 after injecting 10 percent to 50 percent class noise, which is significantly higher than that of the base classifier. These outcomes indicate that the CBR-driven ClusImpute-NoisRes classification learning paradigm provides a viable solution for enterprises, regulatory and policy-making bodies, and market participants to support prediction and warning of financial distress with missing and noisy data.

Details DOI

AAAI Conference 2026 Conference Paper

Conditional Distribution Learning for Graph Classification

Jie Chen
Hua Mao
Chuanbin Liu
Zhu Wang
Xi Peng

Leveraging the diversity and quantity of data provided by various graph-structured data augmentations while preserving intrinsic semantic information is challenging. Additionally, successive layers in graph neural network (GNN) tend to produce more similar node embeddings, while graph contrastive learning aims to increase the dissimilarity between negative pairs of node embeddings. This inevitably results in a conflict between the message-passing mechanism (MPM) of GNNs and the contrastive learning (CL) of negative pairs via intraviews. In this paper, we propose a conditional distribution learning (CDL) method that learns graph representations from graph-structured data for semisupervised graph classification. Specifically, we present an end-to-end graph representation learning model to align the conditional distributions of weakly and strongly augmented features over the original features. This alignment enables the CDL model to effectively preserve intrinsic semantic information when both weak and strong augmentations are applied to graph-structured data. To avoid the conflict between the MPM and the CL of negative pairs, positive pairs of node representations are retained for measuring the similarity between the original features and the corresponding weakly augmented features. Extensive experiments with several benchmark graph datasets demonstrate the effectiveness of the proposed CDL method.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding

Yinglu Li
Zhiying Lu
Zhihang Liu
Yiwei Sun
Chuanbin Liu
Hongtao Xie

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing substantial irrelevant visual content in two ways: 1) Relevant documents often contain large regions unrelated to the query, diluting the focus on salient information; 2) Retrieving multiple documents to increase recall further introduces redundant and irrelevant documents. These redundant contexts distract the model's attention and further degrade the performance. To address this challenge, we propose RegionRAG, a novel framework that shifts the retrieval paradigm from the document level to the region level. During training, we design a hybrid supervision strategy from both labeled data and unlabeled data to pinpoint relevant patches. During inference, we propose a dynamic pipeline that intelligently groups salient patches into complete semantic regions. By delegating the task of identifying relevant regions to the retriever, RegionRAG enables the generator to focus solely on concise, query-relevant visual content, improving both efficiency and accuracy. Experiments on six benchmarks demonstrate that RegionRAG achieves state-of-the-art performance. It improves retrieval accuracy by 10.02% in R@1 on average, and boosts question answering accuracy by 3.56% while using only 71.42% visual tokens compared with prior methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Cross-View Graph Consistency Learning for Invariant Graph Representations

Jie Chen
Hua Mao
Wai Lok Woo
Chuanbin Liu
Xi Peng

Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction. First, two complementary augmented views are derived from an incomplete graph structure through a coupled graph structure augmentation scheme. This augmentation scheme mitigates the potential information loss that is commonly associated with various data augmentation techniques involving raw graph data, such as edge perturbation, node removal, and attribute masking. Second, we propose a CGCL model that can learn invariant graph representations. A cross-view training scheme is proposed to train the proposed CGCL model. This scheme attempts to maximize the consistency information between one augmented view and the graph structure reconstructed from the other augmented view. Furthermore, we offer a comprehensive theoretical CGCL analysis. This paper empirically and experimentally demonstrates the effectiveness of the proposed CGCL method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets

Zhiying Lu
Hongtao Xie
Chuanbin Liu
Yongdong Zhang

There still remains an extreme performance gap between Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) when training from scratch on small datasets, which is concluded to the lack of inductive bias. In this paper, we further consider this problem and point out two weaknesses of ViTs in inductive biases, that is, the spatial relevance and diverse channel representation. First, on spatial aspect, objects are locally compact and relevant, thus fine-grained feature needs to be extracted from a token and its neighbors. While the lack of data hinders ViTs to attend the spatial relevance. Second, on channel aspect, representation exhibits diversity on different channels. But the scarce data can not enable ViTs to learn strong enough representation for accurate recognition. To this end, we propose Dynamic Hybrid Vision Transformer (DHVT) as the solution to enhance the two inductive biases. On spatial aspect, we adopt a hybrid structure, in which convolution is integrated into patch embedding and multi-layer perceptron module, forcing the model to capture the token features as well as their neighboring features. On channel aspect, we introduce a dynamic feature aggregation module in MLP and a brand new "head token" design in multi-head self-attention module to help re-calibrate channel representation and make different channel group representation interacts with each other. The fusion of weak channel representation forms a strong enough representation for classification. With this design, we successfully eliminate the performance gap between CNNs and ViTs, and our DHVT achieves a series of state-of-the-art performance with a lightweight model, 85. 68% on CIFAR-100 with 22. 8M parameters, 82. 3% on ImageNet-1K with 24. 0M parameters. Code is available at https: //github. com/ArieSeirack/DHVT.

PDF Details

AAAI Conference 2020 Conference Paper

CircleNet for Hip Landmark Detection

Hai Wu
Hongtao Xie
Chuanbin Liu
Zheng-Jun Zha
Jun Sun
Yongdong Zhang

Landmark detection plays a critical role in diagnosis of Developmental Dysplasia of the Hip (DDH). Heatmap and anchor-based object detection techniques could obtain reasonable results. However, they have limitations in both robustness and precision given the complexities and inhomogeneity of hip X-ray images. In this paper, we propose a much simpler and more efﬁcient framework called CircleNet to improve the accuracy of landmark detection by predicting landmark and corresponding radius. Using the CircleNet, we not only constrain the relationship between landmarks but also integrate landmark detection and object detection into an end-to-end framework. In order to capture the effective information of the long-range dependency of landmarks in the DDH image, here we propose a new context modeling framework, named the Local Non-Local (LNL) block. The LNL block has the beneﬁts of both non-local block and lightweight computation. We construct a professional DDH dataset for the ﬁrst time and evaluate our CircleNet on it. The dataset has the largest number of DDH X-ray images in the world to our knowledge. Our results show that the CircleNet can achieve the state-of-the-art results for landmark detection on the dataset with a large margin of 1. 8 average pixels compared to current methods. The dataset and source code will be publicly available.

PDF Details

AAAI Conference 2020 Conference Paper

Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization

Chuanbin Liu
Hongtao Xie
Zheng-Jun Zha
Lingfeng Ma
Lingyun Yu
Yongdong Zhang

Delicate attention of the discriminative regions plays a critical role in Fine-Grained Visual Categorization (FGVC). Unfortunately, most of the existing attention models perform poorly in FGVC, due to the pivotal limitations in discriminative regions proposing and region-based feature learning. 1) The discriminative regions are predominantly located based on the ﬁlter responses over the images, which can not be directly optimized with a performance metric. 2) Existing methods train the region-based feature extractor as a one-hot classiﬁcation task individually, while neglecting the knowledge from the entire object. To address the above issues, in this paper, we propose a novel “Filtration and Distillation Learning” (FDL) model to enhance the region attention of discriminate parts for FGVC. Firstly, a Filtration Learning (FL) method is put forward for discriminative part regions proposing based on the matchability between proposing and predicting. Speciﬁcally, we utilize the proposing-predicting matchability as the performance metric of Region Proposal Network (RPN), thus enable a direct optimization of RPN to ﬁltrate most discriminative regions. Go in detail, the objectbased feature learning and region-based feature learning are formulated as “teacher” and “student”, which can furnish better supervision for region-based feature learning. Accordingly, our FDL can enhance the region attention effectively, and the overall framework can be trained end-to-end without neither object nor parts annotations. Extensive experiments verify that FDL yields state-of-the-art performance under the same backbone with the most competitive approaches on several FGVC tasks.

PDF Details