Author name cluster

Chang Zhou

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.

20 papers

2 author rows

AAAI Conference 2026 Conference Paper

Investigating Data Pruning for Pretraining Biological Foundation Models at Scale

Yifan Wu
Jiyue Jiang
Xichen Ye
Yiqi Wang
Chang Zhou
Yitao Xu
Jiayang Chen
He Hu

Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse downstream bioinformatics tasks. However, such models often rely on millions to billions of training sequences and billions of parameters, resulting in prohibitive computational costs and significant barriers to reproducibility and accessibility—particularly for academic labs. To address these challenges, we investigate the feasibility of data pruning for BioFM pretraining and propose a post-hoc influence-guided data pruning framework tailored to biological domains. Our approach first introduces a subset-based self-influence formulation that enables efficient estimation of sample importance at low computational cost. Built upon this, we propose two simple yet effective selection strategies: Top-k Influence (Top I) and Coverage-Centric Influence (CCI). Then, we empirically validate our method on two representative BioFMs: RNA-FM and ESM-C. For RNA, our framework consistently outperforms random selection baselines under an extreme pruning rate of over 99%, which displays our framework's effectiveness. Furthermore, we demonstrate the generalizability of our framework on protein-related tasks using ESM-C. Specifically, our coreset even outperforms random 10x subsets in both RNA and protein settings, revealing substantial redundancy in biological sequence datasets. These findings underscore the potential of influence-guided data pruning to substantially reduce the computational cost of BioFM pretraining, paving the way for more efficient, accessible, and sustainable biological AI research.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RMSAGen: Integrating Multiple Sequence Alignment for Function RNA Design

Jiyue Jiang
Yanyu Chen
Qingchuan Zhang
Jiayi Li
Xiangyu Shi
Chang Zhou
Ziqian Lin
Jiuming Wang

Biological sequences, including RNAs and proteins, share similarities with natural languages, enabling the application of advanced language models to various biological tasks. However, due to its flexibility and lack of experimental data, RNA is a particularly challenging biological ``language'' compared to other biological sequences like proteins. RNA multiple sequence alignments (MSAs), which align evolutionarily related RNA sequences, can greatly enhance RNA biology modeling, as evidenced by their significant roles in structure prediction and function annotation. This raises the question of whether RNA MSAs can also benefit RNA design, which remains unexplored. This paper introduces RMSAGen, a model comprising RMSA-Encoder and RMSA-Decoder, that leverages MSAs to design functional RNA sequences. RMSA-Encoder effectively extracts MSA features, enhancing performance in functional prediction and solvent accessibility prediction tasks and supporting RMSA-Decoder in accurate RNA generation. RMSAGen can design RNA sequences that effectively bind to target RNA-binding proteins, and the design performance improves with an increasing number of sequences. In addition, the ribozymes designed with structural features by RMSAGen show strong computational metrics and exhibit biological activity during gel electrophoresis. These results highlight the effectiveness of RMSAGen, establishing it as a powerful tool and a new direction for RNA design.

PDF Details DOI

EAAI Journal 2025 Journal Article

Automatic collaborative learning for drug repositioning

Yi Wang
Yajie Meng
Chang Zhou
Xianfang Tang
Pan Zeng
Chu Pan
Qiang Zhu
Bengong Zhang

Drug repositioning seeks to identify new therapeutic uses for existing drugs, accelerating development and reducing costs. While traditional wet lab experiments are costly, computational methods offer a low-cost, efficient alternative. Despite their potential, most research in this field has uncritically employed the standard message-passing mechanism of Graph Neural Network (GNN), limiting the assessment of collaborative effects on prediction accuracy. In this paper, we introduce a novel model, an automatic collaborative learning framework for drug repositioning. Initially, we propose a metric to measure the interaction levels among neighbors and integrate it with the intrinsic message-passing mechanism of GNN, thereby enhancing the impact of various collaborative effects on prediction accuracy. Furthermore, we introduce an advanced contrastive learning technique to align feature consistency between the disease–drug association space and the customized neighbor space. This approach leverages the inherent regularities across different feature dimensions to minimize feature redundancy. Extensive experiments conducted on three benchmark datasets demonstrate substantial improvements of this novel model over various state-of-the-art methods. Case studies further highlight the practical utility of this model.

Details DOI

JBHI Journal 2025 Journal Article

Enhancing Drug Repositioning Through Local Interactive Learning With Bilinear Attention Networks

Xianfang Tang
Chang Zhou
Changcheng Lu
Yajie Meng
Junlin Xu
Xinrong Hu
Geng Tian
Jialiang Yang

Drug repositioning has emerged as a promising strategy for identifying new therapeutic applications for existing drugs. In this study, we present DRGBCN, a novel computational method that integrates heterogeneous information through a deep bilinear attention network to infer potential drugs for specific diseases. DRGBCN involves constructing a comprehensive drug-disease network by incorporating multiple similarity networks for drugs and diseases. Firstly, we introduce a layer attention mechanism to effectively learn the embeddings of graph convolutional layers from these networks. Subsequently, a bilinear attention network is constructed to capture pairwise local interactions between drugs and diseases. This combined approach enhances the accuracy and reliability of predictions. Finally, a multi-layer perceptron module is employed to evaluate potential drugs. Through extensive experiments on three publicly available datasets, DRGBCN demonstrates better performance over baseline methods in 10-fold cross-validation, achieving an average area under the receiver operating characteristic curve (AUROC) of 0. 9399. Furthermore, case studies on bladder cancer and acute lymphoblastic leukemia confirm the practical application of DRGBCN in real-world drug repositioning scenarios. Importantly, our experimental results from the drug-disease network analysis reveal the successful clustering of similar drugs within the same community, providing valuable insights into drug-disease interactions. In conclusion, DRGBCN holds significant promise for uncovering new therapeutic applications of existing drugs, thereby contributing to the advancement of precision medicine.

Details DOI

JBHI Journal 2025 Journal Article

SWMA-UNet: Multi-Path Attention Network for Improved Medical Image Segmentation

Xianfang Tang
Jincan Li
Qianrui Liu
Chang Zhou
Pan Zeng
Yajie Meng
Junlin Xu
Geng Tian

In recent years, deep learning achieves significant advancements in medical image segmentation. Research finds that integrating Transformers and CNNs effectively addresses the limitations of CNNs in managing long-distance dependencies and understanding global information. However, existing models typically employ a serial approach to combine Transformers and CNNs, which complicates the simultaneous processing of global and local information. To address this, our study proposes a parallel multi-path attention architecture, SWMA-UNET, that integrates Transformers and CNNs. This architecture deeply mines features through parallel strategies while capturing both local details and global context information, thereby enhancing the accuracy of medical image segmentation. Experimental results indicate that our method surpasses all previously reported methods in the literature on the Synapse, ACDC, ISIC 2018 and MoNuSeg datasets.

Details DOI

AAAI Conference 2024 Conference Paper

Controllable 3D Face Generation with Conditional Style Code Diffusion

Xiaolong Shen
Jianxin Ma
Chang Zhou
Zongxin Yang

Generating photorealistic 3D faces from given conditions is a challenging task. Existing methods often rely on time-consuming one-by-one optimization approaches, which are not efficient for modeling the same distribution content, e.g., faces. Additionally, an ideal controllable 3D face generation model should consider both facial attributes and expressions. Thus we propose a novel approach called TEx-Face(TExt & Expression-to-Face) that addresses these challenges by dividing the task into three components, i.e., 3D GAN Inversion, Conditional Style Code Diffusion, and 3D Face Decoding. For 3D GAN inversion, we introduce two methods, which aim to enhance the representation of style codes and alleviate 3D inconsistencies. Furthermore, we design a style code denoiser to incorporate multiple conditions into the style code and propose a data augmentation strategy to address the issue of insufficient paired visual-language data. Extensive experiments conducted on FFHQ, CelebA-HQ, and CelebA-Dialog demonstrate the promising performance of our TEx-Face in achieving the efficient and controllable generation of photorealistic 3D faces. The code will be publicly available.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

DBPNet: Dual-Branch Parallel Network with Temporal-Frequency Fusion for Auditory Attention Detection

Qinke Ni
Hongyu Zhang
Cunhang Fan
Shengbing Pei
Chang Zhou
Zhao Lv

Auditory attention decoding (AAD) aims to recognize the attended speaker based on electroencephalography (EEG) signals in multi-talker environments. Most AAD methods only focus on the temporal or frequency domain, but neglect the relationships between these two domains, which results in the inability to simultaneously consider both time-varying and spectral-spatial information. To address this issue, this paper proposes a dual-branch parallel network with temporal-frequency fusion for AAD, named DBPNet, which consists of the temporal attentive branch and the frequency residual branch. Specifically, the temporal attentive branch aims to capture the time-varying features in the EEG time-series signal. The frequency residual branch aims to extract spectral-spatial features of multi-band EEG signals by the residual convolution. Finally, these dual branches are fused to consider both EEG signals time-varying and spectral-spatial features and get classification results. Experimental results show that compared with the best baseline, DBPNet achieves a relative improvement of 20. 4% with a 0. 1-second decision window for the MM-AAD dataset, but the number of trainable parameters is reduced by about 91 times.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Sketch and Refine: Towards Fast and Accurate Lane Detection

Chao Chen
Jie Liu
Chang Zhou
Jie Tang
Gangshan Wu

Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effectively and efficiently. Proposal-based methods detect lanes by distinguishing and regressing a collection of proposals in a streamlined top-down way, yet lack sufficient flexibility in lane representation. Keypoint-based methods, on the other hand, construct lanes flexibly from local descriptors, which typically entail complicated post-processing. In this paper, we present a “Sketch-and-Refine” paradigm that utilizes the merits of both keypoint-based and proposal-based methods. The motivation is that local directions of lanes are semantically simple and clear. At the “Sketch” stage, local directions of keypoints can be easily estimated by fast convolutional layers. Then we can build a set of lane proposals accordingly with moderate accuracy. At the “Refine” stage, we further optimize these proposals via a novel Lane Segment Association Module (LSAM), which allows adaptive lane segment adjustment. Last but not least, we propose multi-level feature integration to enrich lane feature representations more efficiently. Based on the proposed “Sketch-and-Refine” paradigm, we propose a fast yet effective lane detector dubbed “SRLane”. Experiments show that our SRLane can run at a fast speed (i.e., 278 FPS) while yielding an F1 score of 78.9%. The source code is available at: https://github.com/passerer/SRLane.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Video Frame Interpolation with Densely Queried Bilateral Correlation

Chang Zhou
Jie Liu
Jie Tang
Gangshan Wu

Video Frame Interpolation (VFI) aims to synthesize non-existent intermediate frames between existent frames. Flow-based VFI algorithms estimate intermediate motion fields to warp the existent frames. Real-world motions' complexity and the reference frame's absence make motion estimation challenging. Many state-of-the-art approaches explicitly model the correlations between two neighboring frames for more accurate motion estimation. In common approaches, the receptive field of correlation modeling at higher resolution depends on the motion fields estimated beforehand. Such receptive field dependency makes common motion estimation approaches poor at coping with small and fast-moving objects. To better model correlations and to produce more accurate motion fields, we propose the Densely Queried Bilateral Correlation (DQBC) that gets rid of the receptive field dependency problem and thus is more friendly to small and fast-moving objects. The motion fields generated with the help of DQBC are further refined and up-sampled with context features. After the motion fields are fixed, a CNN-based SynthNet synthesizes the final interpolated frame. Experiments show that our approach enjoys higher accuracy and less inference time than the state-of-the-art. Source code is available at https: //github. com/kinoud/DQBC.

PDF Details DOI

ICML Conference 2022 Conference Paper

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)

Yu Huang 0023
Junyang Lin
Chang Zhou
Hongxia Yang
Longbo Huang

Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best uni-modal network outperforms the jointly trained multi-modal network across different combinations of modalities on various tasks, which is counter-intuitive since multiple signals would bring more information (Wang et al. , 2020). This work provides a theoretical explanation for the emergence of such performance gap in neural networks for the prevalent joint training framework. Based on a simplified data distribution that captures the realistic property of multi-modal data, we prove that for multi-modal late-fusion network with (smoothed) ReLU activation trained jointly by gradient descent, different modalities will compete with each other and only a subset of modalities will be learned by its corresponding encoder networks. We refer to this phenomenon as modality competition, and the losing modalities, which fail to be discovered, are the origins where the sub-optimality of joint training comes from. In contrast, for uni-modal networks with similar learning settings, we provably show that the networks will focus on learning modality-associated features. Experimentally, we illustrate that modality competition matches the intrinsic behavior of late-fusion joint training to supplement our theoretical results. To the best of our knowledge, our work is the first theoretical treatment towards the degenerating aspect of multi-modal learning in neural networks.

Details

NeurIPS Conference 2022 Conference Paper

Respecting Transfer Gap in Knowledge Distillation

Yulei Niu
Long Chen
Chang Zhou
Hanwang Zhang

Knowledge distillation (KD) is essentially a process of transferring a teacher model's behavior, e. g. , network response, to a student model. The network response serves as additional supervision to formulate the machine domain, which uses the data collected from the human domain as a transfer set. Traditional KD methods hold an underlying assumption that the data collected in both human domain and machine domain are both independent and identically distributed (IID). We point out that this naive assumption is unrealistic and there is indeed a transfer gap between the two domains. Although the gap offers the student model external knowledge from the machine domain, the imbalanced teacher knowledge would make us incorrectly estimate how much to transfer from teacher to student per sample on the non-IID transfer set. To tackle this challenge, we propose Inverse Probability Weighting Distillation (IPWD) that estimates the propensity of a training sample belonging to the machine domain, and assigns its inverse amount to compensate for under-represented samples. Experiments on CIFAR-100 and ImageNet demonstrate the effectiveness of \ours~for both two-stage distillation and one-stage self-distillation.

PDF Details

NeurIPS Conference 2021 Conference Paper

CogView: Mastering Text-to-Image Generation via Transformers

Ming Ding
Zhuoyi Yang
Wenyi Hong
Wendi Zheng
Chang Zhou
Da Yin
Junyang Lin
Xu Zou

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e. g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e. g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

PDF Details

NeurIPS Conference 2021 Conference Paper

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

Zhu Zhang
Jianxin Ma
Chang Zhou
Rui Men
Zhikang Li
Ming Ding
Jie Tang
Jingren Zhou

Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, UFC-BERT, to unify any number of multi-modal controls. In UFC-BERT, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches such as DALL-E and VQGAN, UFC-BERT adopts non-autoregressive generation (NAR) at the second stage to enhance the holistic consistency of the synthesized image, to support preserving specified image blocks, and to improve the synthesis speed. Further, we design a progressive algorithm that iteratively improves the non-autoregressively generated image, with the help of two estimators developed for evaluating the compliance with the controls and evaluating the fidelity of the synthesized image, respectively. Extensive experiments on a newly collected large-scale clothing dataset M2C-Fashion and a facial dataset Multi-Modal CelebA-HQ verify that UFC-BERT can synthesize high-fidelity images that comply with flexible multi-modal controls.

PDF Details

NeurIPS Conference 2020 Conference Paper

CogLTX: Applying BERT to Long Texts

Ming Ding
Chang Zhou
Hongxia Yang
Jie Tang

BERTs are incapable of processing long texts due to its quadratically increasing memory and time consumption. The straightforward thoughts to address this problem, such as slicing the text by a sliding window or simplifying transformers, suffer from insufficient long-range attentions or need customized CUDA kernels. The limited text length of BERT reminds us the limited capacity (5∼ 9 chunks) of the working memory of humans – then how do human beings Cognize Long TeXts? Founded on the cognitive theory stemming from Baddeley, our CogLTX framework identifies key sentences by training a judge model, concatenates them for reasoning and enables multi-step reasoning via rehearsal and decay. Since relevance annotations are usually unavailable, we propose to use treatment experiments to create supervision. As a general algorithm, CogLTX outperforms or gets comparable results to SOTA models on NewsQA, HotpotQA, multi-class and multi-label long-text classification tasks with memory overheads independent of the text length.

PDF Details

ICLR Conference 2020 Conference Paper

Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities

Baichuan Yuan
Xiaowei Wang
Jianxin Ma
Chang Zhou
Andrea L. Bertozzi
Hongxia Yang

Multivariate spatial point process models can describe heterotopic data over space. However, highly multivariate intensities are computationally challenging due to the curse of dimensionality. To bridge this gap, we introduce a declustering based hidden variable model that leads to an efficient inference procedure via a variational autoencoder (VAE). We also prove that this model is a generalization of the VAE-based model for collaborative filtering. This leads to an interesting application of spatial point process models to recommender systems. Experimental results show the method's utility on both synthetic data and real-world data sets.

Details

AAAI Conference 2019 Conference Paper

Deep Interest Evolution Network for Click-Through Rate Prediction

Guorui Zhou
Na Mou
Ying Fan
Qi Pi
Weijie Bian
Chang Zhou
Xiaoqiang Zhu
Kun Gai

Click-through rate (CTR) prediction, whose goal is to estimate the probability of a user clicking on the item, has become one of the core tasks in the advertising system. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, little work considers the changing trend of the interest. In this paper, we propose a novel model, named Deep Interest Evolution Network (DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably, DIEN has been deployed in the display advertisement system of Taobao, and obtained 20. 7% improvement on CTR.

PDF Details

NeurIPS Conference 2019 Conference Paper

Learning Disentangled Representations for Recommendation

Jianxin Ma
Chang Zhou
Peng Cui
Hongxia Yang
Wenwu Zhu

User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users’ decision making processes. The factors are highly entangled, and may range from high-level ones that govern user intentions, to low-level ones that characterize a user’s preference when executing an intention. Learning representations that uncover and disentangle these latent factors can bring enhanced robustness, interpretability, and controllability. However, learning such disentangled representations from user behavior is challenging, and remains largely neglected by the existing literature. In this paper, we present the MACRo-mIcro Disentangled Variational Auto-Encoder (MacridVAE) for learning disentangled representations from user behavior. Our approach achieves macro disentanglement by inferring the high-level concepts associated with user intentions (e. g. , to buy a shirt or a cellphone), while capturing the preference of a user regarding the different concepts separately. A micro-disentanglement regularizer, stemming from an information-theoretic interpretation of VAEs, then forces each dimension of the representations to independently reflect an isolated low-level factor (e. g. , the size or the color of a shirt). Empirical results show that our approach can achieve substantial improvement over the state-of-the-art baselines. We further demonstrate that the learned representations are interpretable and controllable, which can potentially lead to a new paradigm for recommendation where users are given fine-grained control over targeted aspects of the recommendation lists.

PDF Details

AAAI Conference 2018 Conference Paper

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

Chang Zhou
Jinze Bai
Junshuai Song
Xiaofei Liu
Zhengchao Zhao
Xiusi Chen
Jun Gao

A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent the data itself due to limited human instinct. Recent works usually use RNN-based methods to give an overall embedding of a behavior sequence, which then could be exploited by the downstream applications. However, this can only preserve very limited information, or aggregated memories of a person. When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the speciﬁc highly correlated behavior of the user, and introduce noises derived from unrelated behaviors. This paper proposes an attention based user behavior modeling framework called ATRank, which we mainly use for recommendation tasks. Heterogeneous user behaviors are considered in our model that we project all types of behaviors into multiple latent semantic spaces, where inﬂuence can be made among the behaviors via self-attention. Downstream applications then can use the user behavior vectors via vanilla attention. Experiments show that ATRank can achieve better performance and faster training process. We further explore ATRank to use one uniﬁed model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.

PDF Details

IJCAI Conference 2018 Conference Paper

Show and Tell More: Topic-Oriented Multi-Sentence Image Captioning

Yuzhao Mao
Chang Zhou
Xiaojie Wang
Ruifan Li

Image captioning aims to generate textual descriptions for images. Most previous work generates a single-sentence description for each image. However, a picture is worth a thousand words. Single-sentence can hardly give a complete view of an image even by humans. In this paper, we propose a novel Topic-Oriented Multi-Sentence (\emph{TOMS}) captioning model, which can generate multiple topic-oriented sentences to describe an image. Different from object instances or attributes, topics mined by the latent Dirichlet allocation reflect hidden thematic structures in reference sentences of an image. In our model, each topic is integrated to a caption generator with a Fusion Gate Unit (FGU) to guide the generation of a sentence towards a certain topic perspective. With multiple sentences from different topics, our \emph{TOMS} provides a complete description of an image. Experimental results on both sentence and paragraph datasets demonstrate the effectiveness of our \emph{TOMS} in terms of topical consistency and descriptive completeness.

PDF Details

AAAI Conference 2017 Conference Paper

Scalable Graph Embedding for Asymmetric Proximity

Chang Zhou
Yuqiong Liu
Xiaofei Liu
Zhongyi Liu
Jun Gao

Graph Embedding methods are aimed at mapping each vertex into a low dimensional vector space, which preserves certain structural relationships among the vertices in the original graph. Recently, several works have been proposed to learn embeddings based on sampled paths from the graph, e. g. , DeepWalk, Line, Node2Vec. However, their methods only preserve symmetric proximities, which could be insuf- ﬁcient in many applications, even the underlying graph is undirected. Besides, they lack of theoretical analysis of what exactly the relationships they preserve in their embedding space. In this paper, we propose an asymmetric proximity preserving (APP) graph embedding method via random walk with restart, which captures both asymmetric and high-order similarities between node pairs. We give theoretical analysis that our method implicitly preserves the Rooted PageRank score for any two vertices. We conduct extensive experiments on tasks of link prediction and node recommendation on open source datasets, as well as online recommendation services in Alibaba Group, in which the training graph has over 290 million vertices and 18 billion edges, showing our method to be highly scalable and effective.

PDF Details