Taolin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Taolin Zhang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Hanjun Li
Tencent Youtu Lab, Shenzhen, China
2 shared publications - Haoqian Wu
Tencent Youtu Lab
2 shared publications - Ruizhi Qiao
Tencent Youtu Lab
2 shared publications - Taian Guo
Tencent Youtu Lab
2 shared publications - Xing Sun
Tencent Youtu Lab, Shanghai, China
2 shared publications Chen Shi
Platform of AI (PAI) Alibaba
1 shared publication
Latest Publications
- 29 November 2024
- Published by Springer Nature
- p. 391-408
Multimodal Label Relevance Ranking via Reinforcement Learning
- 29 November 2024
- Published by Springer Nature
- p. 391-408
Multimodal Label Relevance Ranking via Reinforcement Learning
- 24 November 2024
- Published by Springer Nature
- p. 346-363
Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
- 24 November 2024
- Published by Springer Nature
- p. 346-363
Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
- Open Access
Multimodal Label Relevance Ranking via Reinforcement Learning
Conventional multi-label recognition methods often focus on label confidence, frequently overlooking the pivotal role of partial order relations consistent with human preference. To resolve these issues, we introduce a novel method for multimodal label relevance ranking, named Label Relevance Ranking with Proximal Policy Optimization (LR\textsuperscript{2}PPO), which effectively discerns partial order relations among labels. LR\textsuperscript{2}PPO first utilizes partial order pairs in the target domain to train a reward model, which aims to capture human preference intrinsic to the specific scenario. Furthermore, we meticulously design state representation and a policy loss tailored for ranking tasks, enabling LR\textsuperscript{2}PPO to boost the performance of label relevance ranking model and largely reduce the requirement of partial order annotation for transferring to new scenes. To assist in the evaluation of our approach and similar methods, we further propose a novel benchmark dataset, LRMovieNet, featuring multimodal labels and their corresponding partial order data. Extensive experiments demonstrate that our LR\textsuperscript{2}PPO algorithm achieves state-of-the-art performance, proving its effectiveness in addressing the multimodal label relevance ranking problem. Codes and the proposed LRMovieNet dataset are publicly available at \url{https://github.com/ChazzyGordon/LR2PPO}.
Open AccessMultimodal Label Relevance Ranking via Reinforcement Learning
Conventional multi-label recognition methods often focus on label confidence, frequently overlooking the pivotal role of partial order relations consistent with human preference. To resolve these issues, we introduce a novel method for multimodal label relevance ranking, named Label Relevance Ranking with Proximal Policy Optimization (LR\textsuperscript{2}PPO), which effectively discerns partial order relations among labels. LR\textsuperscript{2}PPO first utilizes partial order pairs in the target domain to train a reward model, which aims to capture human preference intrinsic to the specific scenario. Furthermore, we meticulously design state representation and a policy loss tailored for ranking tasks, enabling LR\textsuperscript{2}PPO to boost the performance of label relevance ranking model and largely reduce the requirement of partial order annotation for transferring to new scenes. To assist in the evaluation of our approach and similar methods, we further propose a novel benchmark dataset, LRMovieNet, featuring multimodal labels and their corresponding partial order data. Extensive experiments demonstrate that our LR\textsuperscript{2}PPO algorithm achieves state-of-the-art performance, proving its effectiveness in addressing the multimodal label relevance ranking problem. Codes and the proposed LRMovieNet dataset are publicly available at \url{https://github.com/ChazzyGordon/LR2PPO}.
- Open Access
- 13 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (2) , 1-27
FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs
As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, graph data are stored separately in multiple distributed parties in some practical scenarios, which may not be directly shared due to conflicts of interest. Hence, federated graph neural networks are proposed to address such data silo issues while preserving each party’s privacy (or client). Nevertheless, different graph data distributions of various parties, which is known as the statistical heterogeneity, may degrade the performance of naive federated learning algorithms like FedAvg. In this article, we propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above, in which each client will train their local models while also contributing to the training of a global model. FedEgo applies GraphSAGE over ego-graphs to make full use of the structure information and utilizes Mixup for privacy concerns. To deal with the statistical heterogeneity, we integrate personalization into learning and propose an adaptive mixing coefficient strategy that enables clients to achieve their optimal personalization. Extensive experimental results and in-depth analysis demonstrate the effectiveness of FedEgo.
- 13 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (2) , 1-27
Open AccessFedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs
As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, graph data are stored separately in multiple distributed parties in some practical scenarios, which may not be directly shared due to conflicts of interest. Hence, federated graph neural networks are proposed to address such data silo issues while preserving each party’s privacy (or client). Nevertheless, different graph data distributions of various parties, which is known as the statistical heterogeneity, may degrade the performance of naive federated learning algorithms like FedAvg. In this article, we propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above, in which each client will train their local models while also contributing to the training of a global model. FedEgo applies GraphSAGE over ego-graphs to make full use of the structure information and utilizes Mixup for privacy concerns. To deal with the statistical heterogeneity, we integrate personalization into learning and propose an adaptive mixing coefficient strategy that enables clients to achieve their optimal personalization. Extensive experimental results and in-depth analysis demonstrate the effectiveness of FedEgo.
- Open Access
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP). Yet, it is not easy to obtain high-performing models and deploy them online for industrial practitioners. To bridge this gap, EasyNLP is designed to make it easy to build NLP applications, which supports a comprehensive suite of NLP algorithms. It further features knowledge-enhanced pre-training, knowledge distillation and few-shot learning functionalities for large-scale PTMs, and provides a unified framework of model training, inference and deployment for real-world applications. Currently, EasyNLP has powered over ten business units within Alibaba Group and is seamlessly integrated to the Platform of AI (PAI) products on Alibaba Cloud. The source code of our EasyNLP toolkit is released at GitHub (https://github.com/alibaba/EasyNLP).
Open AccessEasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP). Yet, it is not easy to obtain high-performing models and deploy them online for industrial practitioners. To bridge this gap, EasyNLP is designed to make it easy to build NLP applications, which supports a comprehensive suite of NLP algorithms. It further features knowledge-enhanced pre-training, knowledge distillation and few-shot learning functionalities for large-scale PTMs, and provides a unified framework of model training, inference and deployment for real-world applications. Currently, EasyNLP has powered over ten business units within Alibaba Group and is seamlessly integrated to the Platform of AI (PAI) products on Alibaba Cloud. The source code of our EasyNLP toolkit is released at GitHub (https://github.com/alibaba/EasyNLP).
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-314
HfGCN: Hierarchical fused GCN for Joint Entity and Relation Extraction
The extraction of entities and relations from un-structured text is crucial for information extraction. The joint models have been proposed to solve both tasks simultaneously. However, previous work only focuses on the linear representation of sentences and neglects hierarchical grammatical knowledge, which can be injected into the word representations to improve the accuracy of joint extraction. In this paper, we propose a joint model, integrating the fused syntax graph information into a hierarchical graph convolution model for joint extraction. Specifically, we use the attention mechanism to mine the implicit relations between words and dynamically fuse it with explicit dependency syntax graph to obtain fused graph, and through hierarchical graph convolution network to obtain the fused features of different granularity. Experimental results show that our model yields a significant performance compared with prior strong baselines in two datasets.
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-314
HfGCN: Hierarchical fused GCN for Joint Entity and Relation Extraction
The extraction of entities and relations from un-structured text is crucial for information extraction. The joint models have been proposed to solve both tasks simultaneously. However, previous work only focuses on the linear representation of sentences and neglects hierarchical grammatical knowledge, which can be injected into the word representations to improve the accuracy of joint extraction. In this paper, we propose a joint model, integrating the fused syntax graph information into a hierarchical graph convolution model for joint extraction. Specifically, we use the attention mechanism to mine the implicit relations between words and dynamically fuse it with explicit dependency syntax graph to obtain fused graph, and through hierarchical graph convolution network to obtain the fused features of different granularity. Experimental results show that our model yields a significant performance compared with prior strong baselines in two datasets.