Dongping Liao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dongping Liao has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Xitong Gao
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
5 shared publications - Cheng-Zhong Xu
State Key Laboratory of IoTSC, University of Macau, Macau, Macao
4 shared publications - Kejiang Ye
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
2 shared publications Yabo Xu
DataStory Information Technology Co., Ltd
2 shared publications- Guanghui Song
Shenzhen Institutes of Advanced Technology Shenzhen Institutes of Advanced Technology Shenzhen Institutes of Advanced Technology University of Chinese Academy of Sciences Chinese Academy of Sciences University of Macau Imperial College London Chinese Academy of Sciences Shenzhen University of Advanced Technology University of Macau Chinese Academy of Sciences Shenzhen University of Advanced Technology
1 shared publication - Juanjuan Zhao
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
1 shared publication
Latest Publications
- Open Access
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization
Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query Attention (GQA) and token-level KV optimization improve efficiency but rely on rigid resource allocation, often discarding "low-priority" tokens or statically grouping them, failing to address the dynamic spectrum of token importance. We propose mixSGA, a novel mixture-of-expert (MoE) approach that dynamically optimizes token-wise computation and memory allocation. Unlike prior approaches, mixSGA retains all tokens while adaptively routing them to specialized experts with varying KV group sizes, balancing granularity and efficiency. Our key novelties include: (1) a token-wise expert-choice routing mechanism guided by learned importance scores, enabling proportional resource allocation without token discard; (2) weight-sharing across grouped attention projections to minimize parameter overhead; and (3) an auxiliary loss to ensure one-hot routing decisions for training-inference consistency in CLMs. Extensive evaluations across Llama3, TinyLlama, OPT, and Gemma2 model families show mixSGA's superiority over static baselines. On instruction-following and continued pretraining tasks, mixSGA achieves higher ROUGE-L and lower perplexity under the same KV budgets.
Open AccessMixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization
Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query Attention (GQA) and token-level KV optimization improve efficiency but rely on rigid resource allocation, often discarding "low-priority" tokens or statically grouping them, failing to address the dynamic spectrum of token importance. We propose mixSGA, a novel mixture-of-expert (MoE) approach that dynamically optimizes token-wise computation and memory allocation. Unlike prior approaches, mixSGA retains all tokens while adaptively routing them to specialized experts with varying KV group sizes, balancing granularity and efficiency. Our key novelties include: (1) a token-wise expert-choice routing mechanism guided by learned importance scores, enabling proportional resource allocation without token discard; (2) weight-sharing across grouped attention projections to minimize parameter overhead; and (3) an auxiliary loss to ensure one-hot routing decisions for training-inference consistency in CLMs. Extensive evaluations across Llama3, TinyLlama, OPT, and Gemma2 model families show mixSGA's superiority over static baselines. On instruction-following and continued pretraining tasks, mixSGA achieves higher ROUGE-L and lower perplexity under the same KV budgets.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (5) , 5191-5199
Progressive Distribution Matching for Federated Semi-Supervised Learning
Federated Learning (FL) enables collaborative learning from distributed data while preserving the privacy of participating clients. While supervised federated learning with labeled data has made notable strides and achieved success, federated semi-supervised learning (FSSL) lags in its progress. Existing works for FSSL heavily rely on fully-labeled clients, while ignoring the distribution of pseudo-labels generated from skewed unlabeled data. In this work, we offer empirical and theoretical insights into the challenges encountered when applying conventional semi-supervised algorithms in the federated regime. Specifically, we highlight how the inherent data heterogeneity in FSSL can exacerbate issues within the pseudo-labeling process. Motivated by these observations, we propose federated learning with progressive distribution matching (FedPDM) to regularize the distribution of pseudo-labels, aiming to progressively reshape it to align with the ground-truth distribution. The matching problem could be formulated as an optimal transport (OT) problem and efficiently solved by Sinkhorn-Knopp iteration. Through extensive experiments, we demonstrate the superiority of FedPDM on a variety of models and datasets compared with prior arts for FSSL.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (5) , 5191-5199
Open AccessProgressive Distribution Matching for Federated Semi-Supervised Learning
Federated Learning (FL) enables collaborative learning from distributed data while preserving the privacy of participating clients. While supervised federated learning with labeled data has made notable strides and achieved success, federated semi-supervised learning (FSSL) lags in its progress. Existing works for FSSL heavily rely on fully-labeled clients, while ignoring the distribution of pseudo-labels generated from skewed unlabeled data. In this work, we offer empirical and theoretical insights into the challenges encountered when applying conventional semi-supervised algorithms in the federated regime. Specifically, we highlight how the inherent data heterogeneity in FSSL can exacerbate issues within the pseudo-labeling process. Motivated by these observations, we propose federated learning with progressive distribution matching (FedPDM) to regularize the distribution of pseudo-labels, aiming to progressively reshape it to align with the ground-truth distribution. The matching problem could be formulated as an optimal transport (OT) problem and efficiently solved by Sinkhorn-Knopp iteration. Through extensive experiments, we demonstrate the superiority of FedPDM on a variety of models and datasets compared with prior arts for FSSL.
- Open Access
FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
The increasing emphasis on privacy and data security has driven the adoption of federated learning, a decentralized approach to train machine learning models without sharing raw data. Prompt learning, which fine-tunes prompt embeddings of pretrained models, offers significant advantages in federated settings by reducing computational costs and communication overheads while leveraging the strong performance and generalization capabilities of vision-language models such as CLIP. This paper addresses the intersection of federated learning and prompt learning, particularly for vision-language models. In this work, we introduce a comprehensive framework, named FLIP, to evaluate federated prompt learning algorithms. FLIP assesses the performance of 8 state-of-the-art federated prompt learning methods across 4 federated learning protocols and 12 open datasets, considering 6 distinct evaluation scenarios. Our findings demonstrate that prompt learning maintains strong generalization performance in both in-distribution and out-of-distribution settings with minimal resource consumption. This work highlights the effectiveness of federated prompt learning in environments characterized by data scarcity, unseen classes, and cross-domain distributional shifts. We open-source the code for all implemented algorithms in FLIP to facilitate further research in this domain.
Open AccessFLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
The increasing emphasis on privacy and data security has driven the adoption of federated learning, a decentralized approach to train machine learning models without sharing raw data. Prompt learning, which fine-tunes prompt embeddings of pretrained models, offers significant advantages in federated settings by reducing computational costs and communication overheads while leveraging the strong performance and generalization capabilities of vision-language models such as CLIP. This paper addresses the intersection of federated learning and prompt learning, particularly for vision-language models. In this work, we introduce a comprehensive framework, named FLIP, to evaluate federated prompt learning algorithms. FLIP assesses the performance of 8 state-of-the-art federated prompt learning methods across 4 federated learning protocols and 12 open datasets, considering 6 distinct evaluation scenarios. Our findings demonstrate that prompt learning maintains strong generalization performance in both in-distribution and out-of-distribution settings with minimal resource consumption. This work highlights the effectiveness of federated prompt learning in environments characterized by data scarcity, unseen classes, and cross-domain distributional shifts. We open-source the code for all implemented algorithms in FLIP to facilitate further research in this domain.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (4) , 3342-3350
Impartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization
Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from a pretrained teacher to a light-weighted student without original training data. Existing works are limited by a strong assumption that samples used to pretrain the teacher model are balanced, which is, however, unrealistic for many real-world tasks. In this work, we investigated a pragmatic yet under-explored problem: how to perform DFKD from a teacher model pretrained from imbalanced data. We observe a seemingly counter-intuitive phenomenon, i.e., adversarial DFKD algorithms favour minority classes, while causing a disastrous impact on majority classes. We theoretically prove that a biased teacher could cause severe disparity on different groups of synthetic data in adversarial distillation, which further exacerbates the mode collapse of a generator and consequently degenerates the overall accuracy of a distilled student model. To tackle this problem, we propose a class-adaptive regularization method, aiming to encourage impartial representation learning of a generator among different classes under a constrained learning formulation. We devise a primal-dual algorithm to solve the target optimization problem. Through extensive experiments, we show that our method mitigates the biased learning of majority classes in DFKD and improves the overall performance compared with baselines. Code will be available at https://github.com/ldpbuaa/ipad.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (4) , 3342-3350
Open AccessImpartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization
Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from a pretrained teacher to a light-weighted student without original training data. Existing works are limited by a strong assumption that samples used to pretrain the teacher model are balanced, which is, however, unrealistic for many real-world tasks. In this work, we investigated a pragmatic yet under-explored problem: how to perform DFKD from a teacher model pretrained from imbalanced data. We observe a seemingly counter-intuitive phenomenon, i.e., adversarial DFKD algorithms favour minority classes, while causing a disastrous impact on majority classes. We theoretically prove that a biased teacher could cause severe disparity on different groups of synthetic data in adversarial distillation, which further exacerbates the mode collapse of a generator and consequently degenerates the overall accuracy of a distilled student model. To tackle this problem, we propose a class-adaptive regularization method, aiming to encourage impartial representation learning of a generator among different classes under a constrained learning formulation. We devise a primal-dual algorithm to solve the target optimization problem. Through extensive experiments, we show that our method mitigates the biased learning of majority classes in DFKD and improves the overall performance compared with baselines. Code will be available at https://github.com/ldpbuaa/ipad.
- 23 September 2023
- Published by Springer Nature
- p. 3-17
A Survey on Cross-Domain Few-Shot Image Classification
- 23 September 2023
- Published by Springer Nature
- p. 3-17
A Survey on Cross-Domain Few-Shot Image Classification