Xinghao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xinghao Wu has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Jianwei Niu
Beihang University
12 shared publications - Xuefeng Liu
Beihang University, Beijing, China
11 shared publications - Shaojie Tang
Department of Management Science and Systems, University at Buffalo, Buffalo, New York, USA
8 shared publications - Guogang Zhu
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China
5 shared publications Guogang Zhu
Beihang University
4 shared publications- Bo Han
Hong Kong Baptist University
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13376-13384
Mitigating Catastrophic Forgetting in Federated Class-Incremental Learning via Sensitivity-Aware Parameter Partitioning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13376-13384
Open AccessMitigating Catastrophic Forgetting in Federated Class-Incremental Learning via Sensitivity-Aware Parameter Partitioning
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5165-5179
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True and Class-Wise Distillation
Deep neural networks possess remarkable learning capabilities but are vulnerable to overfitting in the presence of mislabeled data. A well-known memorization effect causes networks to first fit clean samples and later memorize noisy labels. Although early stopping can partially alleviate this issue, it cannot prevent the accumulation of incorrect knowledge or recover information lost due to mislabeled inputs. In this paper, we introduce an innovative mechanism for continuous review and timely correction of learned knowledge. Our approach allows the network to repeatedly revisit and reinforce correct information while promptly addressing any inaccuracies stemming from mislabeled data. We present a novel method called self-not-true-distillation (SNTD). This technique employs self-distillation, where the network from previous training iterations acts as a teacher, guiding the current network to review and solidify its understanding of accurate labels. Crucially, SNTD masks the true class label in the logits during this process, concentrating on the non-true classes to correct any erroneous knowledge that may have been acquired. We also recognize that different data classes follow distinct learning trajectories. A single teacher network might struggle to effectively guide the learning of all classes at once, which necessitates selecting different teacher networks for each specific class. Additionally, the influence of the teacher network's guidance varies throughout the training process. To address these challenges, we propose SNTD+, which integrates a class-wise distillation strategy along with a dynamic weight adjustment mechanism. Together, these enhancements significantly bolster SNTD's robustness in tackling complex scenarios characterized by label noise.
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5165-5179
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True and Class-Wise Distillation
Deep neural networks possess remarkable learning capabilities but are vulnerable to overfitting in the presence of mislabeled data. A well-known memorization effect causes networks to first fit clean samples and later memorize noisy labels. Although early stopping can partially alleviate this issue, it cannot prevent the accumulation of incorrect knowledge or recover information lost due to mislabeled inputs. In this paper, we introduce an innovative mechanism for continuous review and timely correction of learned knowledge. Our approach allows the network to repeatedly revisit and reinforce correct information while promptly addressing any inaccuracies stemming from mislabeled data. We present a novel method called self-not-true-distillation (SNTD). This technique employs self-distillation, where the network from previous training iterations acts as a teacher, guiding the current network to review and solidify its understanding of accurate labels. Crucially, SNTD masks the true class label in the logits during this process, concentrating on the non-true classes to correct any erroneous knowledge that may have been acquired. We also recognize that different data classes follow distinct learning trajectories. A single teacher network might struggle to effectively guide the learning of all classes at once, which necessitates selecting different teacher networks for each specific class. Additionally, the influence of the teacher network's guidance varies throughout the training process. To address these challenges, we propose SNTD+, which integrates a class-wise distillation strategy along with a dynamic weight adjustment mechanism. Together, these enhancements significantly bolster SNTD's robustness in tackling complex scenarios characterized by label noise.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3124-3132
Decoupling Dense Video Captioning via Task-specific Prompts
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3124-3132
Open AccessDecoupling Dense Video Captioning via Task-specific Prompts
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18613-18627
The Diversity Bonus: Learning From Dissimilar Clients in Personalized Federated Learning
Personalized federated learning (PFL) allows clients to collaboratively train their personalized models to handle situations where data from different clients are not independent and identically distributed (non-IID). Previous PFL research implicitly assumes that clients benefit most from those with similar data distributions. Correspondingly, methods such as personalized weight aggregation assign higher weights to similar clients during aggregation. We pose a question: can a client benefit from other clients with dissimilar data distributions, and if so, how? This question is particularly relevant in scenarios with a high degree of non-IID, where clients have widely different distributions, and learning from only similar clients will result in a loss of knowledge from many other clients. We note that when dealing with clients with similar distributions, current methods tend to enforce their models to be close in the parameter space. It is reasonable to conjecture that a client can benefit from dissimilar clients if we allow their models to depart from each other. Based on this idea, we propose DiversiFed, which allows each client to learn from clients with diversified distribution. DiversiFed pushes personalized models of clients with dissimilar distributions apart in the parameter space while pulling together those with similar distributions. In addition, to achieve the above effect without using prior knowledge of distribution, we design a loss function that leverages model similarity to determine the degree of attraction and repulsion between any two models. Experiments on benchmark and medical datasets show that DiversiFed can outperform the state-of-the-art (SOTA) methods by up to 3.19%.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18613-18627
The Diversity Bonus: Learning From Dissimilar Clients in Personalized Federated Learning
Personalized federated learning (PFL) allows clients to collaboratively train their personalized models to handle situations where data from different clients are not independent and identically distributed (non-IID). Previous PFL research implicitly assumes that clients benefit most from those with similar data distributions. Correspondingly, methods such as personalized weight aggregation assign higher weights to similar clients during aggregation. We pose a question: can a client benefit from other clients with dissimilar data distributions, and if so, how? This question is particularly relevant in scenarios with a high degree of non-IID, where clients have widely different distributions, and learning from only similar clients will result in a loss of knowledge from many other clients. We note that when dealing with clients with similar distributions, current methods tend to enforce their models to be close in the parameter space. It is reasonable to conjecture that a client can benefit from dissimilar clients if we allow their models to depart from each other. Based on this idea, we propose DiversiFed, which allows each client to learn from clients with diversified distribution. DiversiFed pushes personalized models of clients with dissimilar distributions apart in the parameter space while pulling together those with similar distributions. In addition, to achieve the above effect without using prior knowledge of distribution, we design a loss function that leverages model similarity to determine the degree of attraction and repulsion between any two models. Experiments on benchmark and medical datasets show that DiversiFed can outperform the state-of-the-art (SOTA) methods by up to 3.19%.
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (12) , 10311-10327
3DFaceSculptor: A Common Framework for Image-Guided 3D Face Deformation
We propose 3DFaceSculptor, a general-purpose framework for interactive 3D face editing. Given a source 3D face mesh with semantic materials, and a user-specified semantic image, 3DFaceSculptor can accurately edit the source mesh following the shape guidance of the semantic image, while preserving the source topology as rigid as possible. Recent studies on generating 3D faces focus on learning neural networks to predict 3D shapes, which requires high-cost 3D training datasets. These learning-based methods are limited in compatibility and can only handle face styles involved in the training datasets. Unlike these methods, our 3DFaceSculptor is a non-training and common framework, which only requires supervision from readily-available semantic images, and is compatible with producing various face styles unlimited by datasets. In 3DFaceSculptor, based on the differentiable renderer technique, we deform the source face mesh according to the correspondences between semantic images and mesh materials. However, guiding complex 3D shapes with a simple 2D image incurs extra challenges, that is, the deformation accuracy, surface smoothness, geometric rigidity, and global synchronization of the edited mesh must be guaranteed. To address these challenges, we propose a hierarchical optimization architecture to balance the global and local shape features, and further propose various strategies and losses to improve properties of accuracy, smoothness, rigidity, and so on. Extensive experiments show that our 3DFaceSculptor is able to produce impressive results and has reached the state-of-the-art level.
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (12) , 10311-10327
3DFaceSculptor: A Common Framework for Image-Guided 3D Face Deformation
We propose 3DFaceSculptor, a general-purpose framework for interactive 3D face editing. Given a source 3D face mesh with semantic materials, and a user-specified semantic image, 3DFaceSculptor can accurately edit the source mesh following the shape guidance of the semantic image, while preserving the source topology as rigid as possible. Recent studies on generating 3D faces focus on learning neural networks to predict 3D shapes, which requires high-cost 3D training datasets. These learning-based methods are limited in compatibility and can only handle face styles involved in the training datasets. Unlike these methods, our 3DFaceSculptor is a non-training and common framework, which only requires supervision from readily-available semantic images, and is compatible with producing various face styles unlimited by datasets. In 3DFaceSculptor, based on the differentiable renderer technique, we deform the source face mesh according to the correspondences between semantic images and mesh materials. However, guiding complex 3D shapes with a simple 2D image incurs extra challenges, that is, the deformation accuracy, surface smoothness, geometric rigidity, and global synchronization of the edited mesh must be guaranteed. To address these challenges, we propose a hierarchical optimization architecture to balance the global and local shape features, and further propose various strategies and losses to improve properties of accuracy, smoothness, rigidity, and so on. Extensive experiments show that our 3DFaceSculptor is able to produce impressive results and has reached the state-of-the-art level.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5900-5911
HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5900-5911
Open AccessHtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 13483-13497
Take Your Pick: Enabling Effective Distributed Learning Within Low-Dimensional Feature Space
Personalized federated learning (PFL) is a popular distributed learning framework that allows clients to have different models and has many applications where clients’ data are in different domains, including autonomous driving, traffic surveillance, and medical diagnosis. The typical model of a client in PFL features a global encoder trained by all clients to extract universal features from the raw data and personalized layers (e.g., a classifier) trained using the client’s local data. Nonetheless, due to the differences between the data distributions of different clients (also known as, domain gaps), the universal features produced by the global encoder largely encompass numerous components irrelevant to a certain client’s local task. Some recent PFL methods address the above problem by personalizing specific parameters within the encoder. However, these methods encounter substantial challenges attributed to the high dimensionality and nonlinearity of neural network parameter space. In contrast, the feature space exhibits a lower dimensionality, providing greater intuitiveness and interpretability as compared to the parameter space. To this end, we propose a novel PFL framework named FedPick. FedPick achieves PFL within the low-dimensional feature space by adaptively selecting task-relevant features for each client from the features generated by the global encoder based on its local data distribution. It presents a more accessible and interpretable implementation of PFL compared to those methods working in the parameter space. Extensive experimental results on multiple cross-domain datasets show that FedPick can effectively select task-relevant features for each client and improve model performance in cross-domain FL.
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 13483-13497
Take Your Pick: Enabling Effective Distributed Learning Within Low-Dimensional Feature Space
Personalized federated learning (PFL) is a popular distributed learning framework that allows clients to have different models and has many applications where clients’ data are in different domains, including autonomous driving, traffic surveillance, and medical diagnosis. The typical model of a client in PFL features a global encoder trained by all clients to extract universal features from the raw data and personalized layers (e.g., a classifier) trained using the client’s local data. Nonetheless, due to the differences between the data distributions of different clients (also known as, domain gaps), the universal features produced by the global encoder largely encompass numerous components irrelevant to a certain client’s local task. Some recent PFL methods address the above problem by personalizing specific parameters within the encoder. However, these methods encounter substantial challenges attributed to the high dimensionality and nonlinearity of neural network parameter space. In contrast, the feature space exhibits a lower dimensionality, providing greater intuitiveness and interpretability as compared to the parameter space. To this end, we propose a novel PFL framework named FedPick. FedPick achieves PFL within the low-dimensional feature space by adaptively selecting task-relevant features for each client from the features generated by the global encoder based on its local data distribution. It presents a more accessible and interpretable implementation of PFL compared to those methods working in the parameter space. Extensive experimental results on multiple cross-domain datasets show that FedPick can effectively select task-relevant features for each client and improve model performance in cross-domain FL.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7172-7181
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://github.com/XinghaoWu/FedDecomp
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7172-7181
Open AccessDecoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://github.com/XinghaoWu/FedDecomp
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11060-11069
DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations
In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://github.com/GuogangZhu/DualFed.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11060-11069
Open AccessDualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations
In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://github.com/GuogangZhu/DualFed.
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2601-2609
A SAT-based Method for Counting All Singleton Attractors in Boolean Networks
Boolean networks (BNs) are widely used to model biological regulatory networks. Attractors here hold significant meaning as they represent long-term behaviors such as homeostasis and the results of cell differentiation. As such, computing attractors is of critical importance to guarantee the validity of a model or to assess its stability and robustness. However, this problem is quite challenging when it comes to large real-world models. To overcome the limits of state-of-the-art BDD-based or ASP-based enumeration approaches, we introduce a SAT-based approach to compute fixed points (singleton attractors) of BN and exhibit its merits for counting the number of singleton attractors of large-scale benchmarks well established in the literature.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2601-2609
Open AccessA SAT-based Method for Counting All Singleton Attractors in Boolean Networks
Boolean networks (BNs) are widely used to model biological regulatory networks. Attractors here hold significant meaning as they represent long-term behaviors such as homeostasis and the results of cell differentiation. As such, computing attractors is of critical importance to guarantee the validity of a model or to assess its stability and robustness. However, this problem is quite challenging when it comes to large real-world models. To overcome the limits of state-of-the-art BDD-based or ASP-based enumeration approaches, we introduce a SAT-based approach to compute fixed points (singleton attractors) of BN and exhibit its merits for counting the number of singleton attractors of large-scale benchmarks well established in the literature.