Author name cluster

Wentao Fan

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.

9 papers

1 author row

AAAI Conference 2026 Conference Paper

DRFGD: Disentangled Representation-Focused Generative Defense for Attack-Tolerant Cross-Modal Hashing

Zhongqing Yu
Xin Liu
Yiu-ming Cheung
Zhikai Hu
Wentao Fan
Pan Zhou

With the widespread deployment of cross-modal retrieval in real-world scenarios, ensuring robustness against adversarial attacks is increasingly critical. Remarkably, deep cross-modal hashing is highly vulnerable to adversarial attacks due to its discrete nature and low-dimensional hash codes, while existing defense methods often fail to suppress perturbations embedded in vulnerable features and lack the capacity to model modality-specific structural differences, resulting in suboptimal adversarial robustness. To address these challenges, we propose a novel Disentangled Representation-Focused Generative Defense (DRFGD) framework for attack-tolerant cross-modal hashing. Without altering the structure of retrieval model, DRFGD defends against adversarial attacks by disentangling input representations into adversarial-robust and adversarial-vulnerable components, by an efficient dual-branch semantic-aware encoder. Guided by such disentangled robust features, an attack-tolerant generative module is seamlessly designed to synthesize semantically aligned and perturbation-resilient examples for robust adversarial training, thereby significantly promoting collaborative defense robustness to attackers. Consequently, the semantically consistent hash codes can be well obtained to enhance adversarial robustness in complex cross-modal attacking scenarios. Extensive experiments on public benchmarks demonstrate that DRFGD substantially improves retrieval robustness under various attacking scenarios, and shows its improved defense performance in comparison with the SOTA works.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms

Jiaxun Guo
Manar Amayri
Nizar Bouguila
Xin Liu
Wentao Fan

Recent advances in rotation-invariant (RI) learning for 3D point clouds typically replace raw coordinates with handcrafted RI features to ensure robustness under arbitrary rotations. However, these approaches often suffer from the loss of global pose information, making them incapable of distinguishing geometrically similar but spatially distinct structures. We identify that this limitation stems from the restricted receptive field in existing RI methods, leading to Wing–tip feature collapse, a failure to differentiate symmetric components (e.g., left and right airplane wings) due to indistinguishable local geometries. To overcome this challenge, we introduce the Shadow-informed Pose Feature (SiPF), which augments local RI descriptors with a globally consistent reference point (referred to as the “shadow”) derived from a learned shared rotation. This mechanism enables the model to preserve global pose awareness while maintaining rotation invariance. We further propose Rotation-invariant Attention Convolution (RIAttnConv), an attention-based operator that integrates SiPFs into the feature aggregation process, thereby enhancing the model’s capacity to distinguish structurally similar components. Additionally, we design a task-adaptive shadow locating module based on the Bingham distribution over unit quaternions, which dynamically learns the optimal global rotation for constructing consistent shadows. Extensive experiments on 3D classification and part segmentation benchmarks demonstrate that our approach substantially outperforms existing RI methods, particularly in tasks requiring fine-grained spatial discrimination under arbitrary rotations.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Online Cross-Modal Hashing with Expanding Label Space

Wentao Fan
Chao Zhang
Chunlin Chen
Huaxiong Li

Due to the continuous increase of multimedia data on the internet, online hashing has garnered considerable attention for handling multi-modal data streams. However, most existing online hashing approaches focus solely on data growth of samples, overlooking the dynamics of classes. In this paper, we simultaneously address the challenges of both sample-level and class-level growth, and propose a novel Online Hashing method with Expanding Label Space (OH-ELS) for cross-modal retrieval. In OH-ELS, multi-modal data arrives continuously, and incoming data may introduce new classes. To avoid catastrophic forgetting, we transfer the historical knowledge at both the sample and class levels. At the sample-level, a small subset of anchor codes from old data are replayed to preserve the similarities between new data and old data. At the class-level, a consistency regularizer is applied to new classifiers to leverage the priors of historical classes. To ensure both efficiency and accuracy, a discrete optimization algorithm is proposed to solve the binary-constrained optimization problem without relaxation. Experimental results illustrate the effectiveness and superiority of OH-ELS in class-incremental cross-modal retrieval compared with the state-of-the-art methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Semantic-Aware Feature Enhancement for Partial Label Learning

Haowei Mei
Chao Zhang
Wentao Fan
Xiuyi Jia
Chunlin Chen
Huaxiong Li

Partial label learning (PLL) aims to learn from the data where each instance is associated with a candidate label set, with only one being valid. Most existing approaches are designed to eliminate noisy labels and use the remaining reliable ones for model training, following a label-centric learning paradigm. In this paper, we propose a new PLL method called Semantic-Aware Feature Enhancement (SAFE), which tackles the problem through a novel feature-centric learning paradigm. SAFE presumes that the candidate labels are correct while the observed features are partial, and thus seeks to recover the underlying missing features. In this manner, a desired predictive model is constructed by integrating the observed and recovered features, which are responsible for predicting the true label and the remaining candidate labels, respectively. To ensure the quality of recovered features, SAFE jointly explores the intrinsic topological structures via dynamic graphs in both feature and label spaces as guidance for semantic-aware feature enhancement. Extensive experimental results on some popular datasets demonstrate the effectiveness and superiority of the proposed method over state-of-the-art PLL approaches.

PDF Details DOI

EAAI Journal 2023 Journal Article

Uncertainty quantification in molecular property prediction through spherical mixture density networks

Wentao Fan
Lidan Zeng
Tian Wang

As uncertainty quantification is crucial for determining undesirable inputs and improving decisions made by a system to acquire accurate evaluations, it has received much attention in recent years. Motivated by the fact that probability is one of the most effective ways to estimate uncertainty, in this work we propose an effective probabilistic model for quantifying predictive uncertainty in the task of predicting chemical molecular properties. Our model is formulated by developing a spherical mixture density network that is composed of von Mises-Fisher kernel distributions to model graph-structured molecule representations. Furthermore, an ensemble framework for spherical mixture density networks is developed, which can yield high quality predictive uncertainty estimates and obtain better confidence intervals reflecting the sources of these uncertainties in predictions. The effectiveness of our approach in modeling the output predictive uncertainty is validated through empirical analysis on molecular property prediction tasks with two publicly available chemical molecule data sets. Comparing with the current state-of-the-art baselines, our model can better model predictive uncertainty in terms of higher log-likelihood of the data, and reveal that there might be more than one acceptable chemical property associated with an input molecule representation.

Details DOI

EAAI Journal 2022 Journal Article

A complex Jensen–Shannon divergence in complex evidence theory with its application in multi-source information fusion

Wentao Fan
Fuyuan Xiao

Multi-source information fusion has attracted considerable attention in the few past years and plays a great role in real applications. However, the uncertainty or conflict will make the fusion results unreasonable. Furthermore, the information may be collected in the form of complex number that cannot be processed by existing methods. In this article, to handle the above issues, the complex evidence theory (CET) is exploited. CET is the generalization of Dempster–Shafer evidence theory, where the mass function is modeled by complex number, called complex mass function (CMF). In order to deal with multi-source information fusion from the perspective of the complex plane, a new Complex Jensen–Shannon divergence (CJS divergence) is presented in this article. The proposed CJS divergence can effectively measure the conflict between two CMFs, and it satisfies the properties of boundedness, symmetry and nondegeneracy. In addition, for a better combination result, we have adjusted the complex Dempster’s rule of combination, which is called the reinforced complex evidence combination rule (RCECR). Then an algorithm for multi-source information fusion is proposed based on the CJS divergence and the RCECR. Some numerical examples and two applications in target identification and medical diagnosis illustrate the effectiveness of the new approach.

Details DOI

EAAI Journal 2020 Journal Article

Spherical data clustering and feature selection through nonparametric Bayesian mixture models with von Mises distributions

Wentao Fan
Nizar Bouguila

In this work, we tackle the problem of clustering spherical (i. e. L 2 normalized) data vectors using nonparametric Bayesian mixture models with von Mises distributions. Our model is formulated by employing a nonparametric Bayesian framework known as the Pitman–Yor process mixture model. Different from finite mixture models in which the determination of the number of clusters is a crucial problem and often requires extra effort (e. g. by inspecting information criteria), the proposed model is nonparametric such that the number of clusters in the model is assumed to be infinite at the initial stage and will be inferred automatically based on the data. Moreover, an unsupervised feature selection scheme is incorporated into the proposed model to remove features that do not contribute significantly to the clustering process. We develop a stochastic variational inference algorithm to estimate model parameters, model complexity and feature saliencies simultaneously and effectively through the method of stochastic gradient ascent. We demonstrate the merits of the proposed nonparametric Bayesian mixture model on clustering spherical data vectors by conducting experiments on both synthetic datasets and two real-world applications namely topic novelty detection and flower images categorization.

Details DOI

EAAI Journal 2015 Journal Article

Expectation propagation learning of a Dirichlet process mixture of Beta-Liouville distributions for proportional data clustering

Wentao Fan
Nizar Bouguila

We propose a nonparametric Bayesian model for the clustering of proportional data. Our model is based on an infinite mixture of Beta-Liouville distributions and allows a compact description of complex data. The choice of the Beta-Liouville as the basis of our model is justified by the fact that it has been shown to be a good alternative to the Dirichlet and generalized Dirichlet distributions for the statistical representation of proportional data. Using this infinite mixture, we show how a careful modeling can achieve good results by allowing the elicitation of prior belief about the parameters and the number of clusters through suitable learning. Indeed, we develop an efficient learning algorithm, based on expectation propagation, to estimate the parameters of our infinite Beta-Liouville mixture model. The feasibility and effectiveness of the proposed method are demonstrated by two challenging applications namely action and facial expression recognition.

Details DOI

IJCAI Conference 2013 Conference Paper

Learning Finite Beta-Liouville Mixture Models via Variational Bayes for Proportional Data Clustering

Wentao Fan
Nizar Bouguila

During the past decade, ﬁnite mixture modeling has become a well-established technique in data analysis and clustering. This paper focus on developing a variational inference framework to learn ﬁnite Beta-Liouville mixture models that have been proposed recently as an efﬁcient way for proportional data clustering. In contrast to the conventional expectation maximization (EM) algorithm, commonly used for learning ﬁnite mixture models, the proposed algorithm has the advantages that it is more efﬁcient from a computational point of view and by preventing over- and under-ﬁtting problems. Moreover, the complexity of the mixture model (i. e. the number of components) can be determined automatically and simultaneously with the parameters estimation in a closed form as part of the Bayesian inference procedure. The merits of the proposed approach are shown using both arti- ﬁcial data sets and two interesting and challenging real applications namely dynamic textures clustering and facial expression recognition.

PDF Details DOI