Xinting Liao (廖馨婷) Xenia Liao

Zhejiang University Ph.D, Zhejiang University (2025)

I am Xinting (Xenia) Liao. I study at Zhejiang University and work under the supervision of Prof. Xiaolin Zheng and Chaochao Chen. Now I participate in the joint Ph.D. program in National University of Singapore with the supervision of Prof. Tat-Seng Chua and collaboration with Dr. Wenjie Wang. My research interests are computer vision, LLM, privacy-computing, federated learning, trustworthy machine learning.
I am currently seeking a Postdoctoral opportunity or research scientist position.

Google Scholar Semantic Scholar GitHub Resume ORCID
Education
  • Zhejiang University

    Zhejiang University

    Ph.D. in Computer Science Sep. 2020 - Jul. 2025

  • Sichuan University

    Sichuan University

    B.S. in Software Engineering Sep. 2016 - Jul. 2020

Experience
  • Next++ Lab in National University of Singapore

    Next++ Lab in National University of Singapore

    Visiting student Jun. 2024 - Present

  • Text Intelligence Lab in Westlake University

    Text Intelligence Lab in Westlake University

    Visiting student Oct. 2019 - May. 2020

  • Medical Image Lab in Sichuan University

    Medical Image Lab in Sichuan University

    Research intern Mar. 2018 - Jun. 2019

Service
  • Reviewer of ACM MM, ACL, EMNLP, NeurIPS, ICLR, AISTATS
News
  • Sept. 2024. One paper got accepted by NeurIPS2024.
Selected Publications (view all )
FOOGD:Federated Collaboration for Both Out-of-distribution Generalization and Detection
FOOGD:Federated Collaboration for Both Out-of-distribution Generalization and Detection

Xinting Liao, Weiming Liu, Pengyang Zhou, Fengyuan Yu, Jiahe Xu, Jun Wang, Wenjie Wang, Chaochao Chen, Xiaolin Zheng†(† corresponding author)

Advances in Neural Information Processing Systems 2024 CCF A ConferencePoster

WFederated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenarios remains unreliable due to the coexistence of in-distribution data and unexpected out-of-distribution (OOD) data, such as covariate-shift and semantic-shift data. Current FL researches typically address either covariate-shift data through OOD generalization or semantic-shift data via OOD detection, overlooking the simultaneous occurrence of various OOD shifts. In this work, we propose FOOGD, a method that estimates the probability density of each client and obtains reliable global distribution as guidance for the subsequent FL process. Firstly, SM3D in FOOGD estimates score model for arbitrary distributions without prior constraints, and detects semantic-shift data powerfully. Then SAG in FOOGD provides invariant yet diverse knowledge for both local covariate-shift generalization and client performance generalization. In empirical validations, FOOGD significantly enjoys three main advantages: (1) reliably estimating non-normalized decentralized distributions, (2) detecting semantic shift data via score values, and (3) generalizing to covariate-shift data by regularizing feature extractor. The prejoct is open in 🔗Github.

[Code] [Paper] [Cite]

FOOGD:Federated Collaboration for Both Out-of-distribution Generalization and Detection
FOOGD:Federated Collaboration for Both Out-of-distribution Generalization and Detection

Xinting Liao, Weiming Liu, Pengyang Zhou, Fengyuan Yu, Jiahe Xu, Jun Wang, Wenjie Wang, Chaochao Chen, Xiaolin Zheng†(† corresponding author)

Advances in Neural Information Processing Systems 2024 CCF A ConferencePoster

WFederated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenarios remains unreliable due to the coexistence of in-distribution data and unexpected out-of-distribution (OOD) data, such as covariate-shift and semantic-shift data. Current FL researches typically address either covariate-shift data through OOD generalization or semantic-shift data via OOD detection, overlooking the simultaneous occurrence of various OOD shifts. In this work, we propose FOOGD, a method that estimates the probability density of each client and obtains reliable global distribution as guidance for the subsequent FL process. Firstly, SM3D in FOOGD estimates score model for arbitrary distributions without prior constraints, and detects semantic-shift data powerfully. Then SAG in FOOGD provides invariant yet diverse knowledge for both local covariate-shift generalization and client performance generalization. In empirical validations, FOOGD significantly enjoys three main advantages: (1) reliably estimating non-normalized decentralized distributions, (2) detecting semantic shift data via score values, and (3) generalizing to covariate-shift data by regularizing feature extractor. The prejoct is open in 🔗Github.

[Code] [Paper] [Cite]

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data
Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data

Xinting Liao, Weiming Liu, Chaochao Chen†, Pengyang Zhou, Fengyuan Yu, Huabin Zhu, Binhui Yao, Tao Wang, Xiaolin Zheng, Yanchao Tan(† corresponding author)

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 CCF A ConferencePoster

Federated learning achieves effective performance in modeling decentralized data. In practice client data are not well-labeled which makes it potential for federated unsupervised learning (FUSL) with non-IID data. However the performance of existing FUSL methods suffers from insufficient representations i.e. (1) representation collapse entanglement among local and global models and (2) inconsistent representation spaces among local models. The former indicates that representation collapse in local model will subsequently impact the global model and other local models. The latter means that clients model data representation with inconsistent parameters due to the deficiency of supervision signals. In this work we propose FedU2 which enhances generating uniform and unified representation in FUSL with non-IID data. Specifically FedU2 consists of flexible uniform regularizer (FUR) and efficient unified aggregator (EUA). FUR in each client avoids representation collapse via dispersing samples uniformly and EUA in server promotes unified representation by constraining consistent client model updating. To extensively validate the performance of FedU2 we conduct both cross-device and cross-silo evaluation experiments on two benchmark datasets i.e. CIFAR10 and CIFAR100.

[Paper] [Cite] [Code]

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data
Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data

Xinting Liao, Weiming Liu, Chaochao Chen†, Pengyang Zhou, Fengyuan Yu, Huabin Zhu, Binhui Yao, Tao Wang, Xiaolin Zheng, Yanchao Tan(† corresponding author)

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 CCF A ConferencePoster

Federated learning achieves effective performance in modeling decentralized data. In practice client data are not well-labeled which makes it potential for federated unsupervised learning (FUSL) with non-IID data. However the performance of existing FUSL methods suffers from insufficient representations i.e. (1) representation collapse entanglement among local and global models and (2) inconsistent representation spaces among local models. The former indicates that representation collapse in local model will subsequently impact the global model and other local models. The latter means that clients model data representation with inconsistent parameters due to the deficiency of supervision signals. In this work we propose FedU2 which enhances generating uniform and unified representation in FUSL with non-IID data. Specifically FedU2 consists of flexible uniform regularizer (FUR) and efficient unified aggregator (EUA). FUR in each client avoids representation collapse via dispersing samples uniformly and EUA in server promotes unified representation by constraining consistent client model updating. To extensively validate the performance of FedU2 we conduct both cross-device and cross-silo evaluation experiments on two benchmark datasets i.e. CIFAR10 and CIFAR100.

[Paper] [Cite] [Code]

FedRANE:Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
FedRANE:Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data

Xinting Liao, Chaochao Chen†, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng(† corresponding author)

Proceedings of the 31st ACM International Conference on Multimedia (MM) 2023 CCF A ConferenceOral

FFederated learning (FL) is a distributed machine learning paradigm that needs collaboration between a server and a series of clients with decentralized data. To make FL effective in real-world applications, existing work devotes to improving the modeling of decentralized non-IID data. In non-IID settings, there are intra-client inconsistency that comes from the imbalanced data modeling, and inter-client inconsistency among heterogeneous client distributions, which not only hinders sufficient representation of the minority data, but also brings discrepant model deviations. However, previous work overlooks to tackle the above two coupling inconsistencies together. In this work, we propose FedRANE, which consists of two main modules, i.e., local relational augmentation (LRA) and global Nash equilibrium (GNE), to resolve intra-and inter-client inconsistency simultaneously. Specifically, in each client, LRA mines the similarity relations among different data samples and enhances the minority sample representations with their neighbors using attentive message passing. In server, GNE reaches an agreement among inconsistent and discrepant model deviations from clients to server, which encourages the global model to update in the direction of global optimum without breaking down the clients' optimization toward their local optimums. We conduct extensive experiments on four benchmark datasets to show the superiority of FedRANE in enhancing the performance of FL with non-IID data.

[Paper] [Cite] [Code]

FedRANE:Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
FedRANE:Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data

Xinting Liao, Chaochao Chen†, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng(† corresponding author)

Proceedings of the 31st ACM International Conference on Multimedia (MM) 2023 CCF A ConferenceOral

FFederated learning (FL) is a distributed machine learning paradigm that needs collaboration between a server and a series of clients with decentralized data. To make FL effective in real-world applications, existing work devotes to improving the modeling of decentralized non-IID data. In non-IID settings, there are intra-client inconsistency that comes from the imbalanced data modeling, and inter-client inconsistency among heterogeneous client distributions, which not only hinders sufficient representation of the minority data, but also brings discrepant model deviations. However, previous work overlooks to tackle the above two coupling inconsistencies together. In this work, we propose FedRANE, which consists of two main modules, i.e., local relational augmentation (LRA) and global Nash equilibrium (GNE), to resolve intra-and inter-client inconsistency simultaneously. Specifically, in each client, LRA mines the similarity relations among different data samples and enhances the minority sample representations with their neighbors using attentive message passing. In server, GNE reaches an agreement among inconsistent and discrepant model deviations from clients to server, which encourages the global model to update in the direction of global optimum without breaking down the clients' optimization toward their local optimums. We conduct extensive experiments on four benchmark datasets to show the superiority of FedRANE in enhancing the performance of FL with non-IID data.

[Paper] [Cite] [Code]

PPGenCDR:Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation
PPGenCDR:Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation

Xinting Liao, Weiming Liu, Xiaolin Zheng, Binhui Yao, Chaochao Chen†(† corresponding author)

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2023 CCF A ConferenceOral

Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems. Existing work on cross-domain recommendation (CDR) reaches advanced and satisfying recommendation performance, but mostly neglects preserving privacy. To fill this gap, we propose a privacy-preserving generative cross-domain recommendation (PPGenCDR) framework for PPCDR. PPGenCDR includes two main modules, i.e., stable privacy-preserving generator module, and robust cross-domain recommendation module. Specifically, the former isolates data from different domains with a generative adversarial network (GAN) based model, which stably estimates the distribution of private data in the source domain with ́Renyi differential privacy (RDP) technique. Then the latter aims to robustly leverage the perturbed but effective knowledge from the source domain with the raw data in target domain to improve recommendation performance. Three key modules, i.e., (1) selective privacy preserver, (2) GAN stabilizer, and (3) robustness conductor, guarantee the cost-effective trade-off between utility and privacy, the stability of GAN when using RDP, and the robustness of leveraging transferable knowledge accordingly. The extensive empirical studies on Douban and Amazon datasets demonstrate that PPGenCDR significantly outperforms the state-of-the-art recommendation models while preserving privacy.

[Paper] [Cite] [Code]

PPGenCDR:Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation
PPGenCDR:Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation

Xinting Liao, Weiming Liu, Xiaolin Zheng, Binhui Yao, Chaochao Chen†(† corresponding author)

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2023 CCF A ConferenceOral

Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems. Existing work on cross-domain recommendation (CDR) reaches advanced and satisfying recommendation performance, but mostly neglects preserving privacy. To fill this gap, we propose a privacy-preserving generative cross-domain recommendation (PPGenCDR) framework for PPCDR. PPGenCDR includes two main modules, i.e., stable privacy-preserving generator module, and robust cross-domain recommendation module. Specifically, the former isolates data from different domains with a generative adversarial network (GAN) based model, which stably estimates the distribution of private data in the source domain with ́Renyi differential privacy (RDP) technique. Then the latter aims to robustly leverage the perturbed but effective knowledge from the source domain with the raw data in target domain to improve recommendation performance. Three key modules, i.e., (1) selective privacy preserver, (2) GAN stabilizer, and (3) robustness conductor, guarantee the cost-effective trade-off between utility and privacy, the stability of GAN when using RDP, and the robustness of leveraging transferable knowledge accordingly. The extensive empirical studies on Douban and Amazon datasets demonstrate that PPGenCDR significantly outperforms the state-of-the-art recommendation models while preserving privacy.

[Paper] [Cite] [Code]

HyperFed:hyperbolic prototypes exploration with consistent aggregation for non-IID data in federated learning
HyperFed:hyperbolic prototypes exploration with consistent aggregation for non-IID data in federated learning

Xinting Liao, Weiming Liu, Chaochao Chen†, Pengyang Zhou, Huabin Zhu, Yanchao Tan, Jun Wang, Yue Qi(† corresponding author)

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI) 2023 CCF A ConferenceOral

Federated learning (FL) collaboratively models user data in a decentralized way. However, in the real world, non-identical and independent data distributions (non-IID) among clients hinder the performance of FL due to three issues, i.e., (1) the class statistics shifting, (2) the insufficient hierarchical information utilization, and (3) the inconsistency in aggregating clients. To address the above issues, we propose HyperFed which contains three main modules, i.e., hyperbolic prototype Tammes initialization (HPTI), hyperbolic prototype learning (HPL), and consistent aggregation (CA). Firstly, HPTI in the server constructs uniformly distributed and fixed class prototypes, and shares them with clients to match class statistics, further guiding consistent feature representation for local clients. Secondly, HPL in each client captures the hierarchical information in local data with the supervision of shared class prototypes in the hyperbolic model space. Additionally, CA in the server mitigates the impact of the inconsistent deviations from clients to server. Extensive studies of four datasets prove that HyperFed is effective in enhancing the performance of FL under the non-IID setting.

[Paper] [Cite] [Code]

HyperFed:hyperbolic prototypes exploration with consistent aggregation for non-IID data in federated learning
HyperFed:hyperbolic prototypes exploration with consistent aggregation for non-IID data in federated learning

Xinting Liao, Weiming Liu, Chaochao Chen†, Pengyang Zhou, Huabin Zhu, Yanchao Tan, Jun Wang, Yue Qi(† corresponding author)

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI) 2023 CCF A ConferenceOral

Federated learning (FL) collaboratively models user data in a decentralized way. However, in the real world, non-identical and independent data distributions (non-IID) among clients hinder the performance of FL due to three issues, i.e., (1) the class statistics shifting, (2) the insufficient hierarchical information utilization, and (3) the inconsistency in aggregating clients. To address the above issues, we propose HyperFed which contains three main modules, i.e., hyperbolic prototype Tammes initialization (HPTI), hyperbolic prototype learning (HPL), and consistent aggregation (CA). Firstly, HPTI in the server constructs uniformly distributed and fixed class prototypes, and shares them with clients to match class statistics, further guiding consistent feature representation for local clients. Secondly, HPL in each client captures the hierarchical information in local data with the supervision of shared class prototypes in the hyperbolic model space. Additionally, CA in the server mitigates the impact of the inconsistent deviations from clients to server. Extensive studies of four datasets prove that HyperFed is effective in enhancing the performance of FL under the non-IID setting.

[Paper] [Cite] [Code]

All publications