Jing Tao
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
Research Subjects
Jing Tao has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Pinghui Wang
Xi'an Jiaotong University, Xi'an, China
22 shared publications - Xiaohong Guan
Xi'an Jiaotong University, Xi'an, China
16 shared publications - Junzhou Zhao
MOE Key Laboratory for Intelligent Networks and Network Security, Xian Jiaotong University, Xian, China
7 shared publications - Peng Jia
MOE Key Laboratory for Intelligent Networks and Network Security, Xian Jiaotong University, Xian, Shaanxi, China
5 shared publications - Feiyang Sun
MOE KLINNS Lab, Xi’an Jiaotong University, Xi’an, China
2 shared publications - Jie Ma
MOE KLINNS Lab Xi'an Jiaotong University
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6397-6408
MCoRe: Multi-Entry Complementary Retrieval with Reflection-Guided Iteration for Multi-Hop QA
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6397-6408
Open AccessMCoRe: Multi-Entry Complementary Retrieval with Reflection-Guided Iteration for Multi-Hop QA
- 16 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109133
Mapp: A model-agnostic privacy-preserving framework for two-party graph neural network inference
- 16 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109133
Mapp: A model-agnostic privacy-preserving framework for two-party graph neural network inference
- Open Access
- 26 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (1) , 1-32
Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
Legal Judgment Prediction (LJP) aims to automatically predict a law case’s judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work’s further finding. This article proposes an end-to-end model named D-LADAN to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operator (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.
- 26 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (1) , 1-32
Open AccessDistinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
Legal Judgment Prediction (LJP) aims to automatically predict a law case’s judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work’s further finding. This article proposes an end-to-end model named D-LADAN to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operator (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.
- Open Access
Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
Legal Judgment Prediction (LJP) aims to automatically predict a law case's judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work's further finding. This paper proposes an end-to-end model named \textit{D-LADAN} to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operation (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.
Open AccessDistinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
Legal Judgment Prediction (LJP) aims to automatically predict a law case's judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work's further finding. This paper proposes an end-to-end model named \textit{D-LADAN} to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operation (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 434-445
Memory Disagreement: A Pseudo-Labeling Measure from Training Dynamics for Semi-supervised Graph Learning
In the realm of semi-supervised graph learning, pseudo-labeling is a pivotal strategy to utilize both labeled and unlabeled nodes for model training. Currently, confidence score is the most frequently used pseudo-labeling measure, however, it suffers from poor calibration and issues in out-of-distribution data. In this paper, we propose memory disagreement (MoDis for short), a novel uncertainty measure for pseudo-labeling. We uncover that training dynamics offer significant insights into prediction uncertainty --- if a graph model makes consistent predictions for an unlabeled node throughout training, the corresponding predicted label is likely to be correct. Thus, the node should be suitable for pseudo-labeling. The basic idea is supported by recent studies on training dynamics. We implement MoDis as the entropy of an accumulated distribution that summarizes the disagreement of the model's predictions throughout training. We further enhance and analyze MoDis in case studies, which show nodes with low MoDis are suitable for pseudo-labeling as these nodes tend to be distant from boundaries in both graph and representation space. We design MoDis based pseudo-label selection algorithm and corresponding pseudo-labeling algorithm, which are applicable to various graph neural networks. We empirically validate MoDis on eight benchmark graph datasets. The experimental results show that pseudo labels given by MoDis have better quality in correctness and information gain, and the algorithm benefits various graph neural networks, achieving an average relative improvement of 3.11% and reaching up to 30.24% when compared to the wildly-used uncertainty measure, confidence score. Moreover, we demonstrate the efficacy of MoDis on out-of-distribution nodes.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 434-445
Open AccessMemory Disagreement: A Pseudo-Labeling Measure from Training Dynamics for Semi-supervised Graph Learning
In the realm of semi-supervised graph learning, pseudo-labeling is a pivotal strategy to utilize both labeled and unlabeled nodes for model training. Currently, confidence score is the most frequently used pseudo-labeling measure, however, it suffers from poor calibration and issues in out-of-distribution data. In this paper, we propose memory disagreement (MoDis for short), a novel uncertainty measure for pseudo-labeling. We uncover that training dynamics offer significant insights into prediction uncertainty --- if a graph model makes consistent predictions for an unlabeled node throughout training, the corresponding predicted label is likely to be correct. Thus, the node should be suitable for pseudo-labeling. The basic idea is supported by recent studies on training dynamics. We implement MoDis as the entropy of an accumulated distribution that summarizes the disagreement of the model's predictions throughout training. We further enhance and analyze MoDis in case studies, which show nodes with low MoDis are suitable for pseudo-labeling as these nodes tend to be distant from boundaries in both graph and representation space. We design MoDis based pseudo-label selection algorithm and corresponding pseudo-labeling algorithm, which are applicable to various graph neural networks. We empirically validate MoDis on eight benchmark graph datasets. The experimental results show that pseudo labels given by MoDis have better quality in correctness and information gain, and the algorithm benefits various graph neural networks, achieving an average relative improvement of 3.11% and reaching up to 30.24% when compared to the wildly-used uncertainty measure, confidence score. Moreover, we demonstrate the efficacy of MoDis on out-of-distribution nodes.
- 30 November 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (5) , 1578-1591
Diagram Perception Networks for Textbook Question Answering via Joint Optimization
- 30 November 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (5) , 1578-1591
Diagram Perception Networks for Textbook Question Answering via Joint Optimization
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0969-0974
Balanced Hashgraph Based on Dynamic MCMC: Efficient, Practical and Compatible
In a blockchain system based on the HashGraph consensus algorithm, picking a target server for block propagation is a key step. The traditional HashGraph blockchain system uses a completely random approach to pick the target server, which has the advantage of ensuring the security of the system and reducing the impact of attacks and single server failures received by the system. However, the random selection of target servers may lead to a situation where low performance servers are under high load but high performance servers are under load. In order to make each server process the block data with maximum performance, this paper proposes a balanced up-linking strategy, which calculates the server's reputation by evaluating the status of four dimensions, such as remaining performance, security, response time, and trustworthiness of the server, and then constructs a geometric probability model by Markov model and Monte Carlo method, so that the block is randomly propagated to each server with a specific probability according to the server status. In the process of running the blockchain system with this strategy, the probability of propagation to each server is dynamically adjusted according to the changing server status, so that the frequency distribution of all servers in the cluster receiving blocks obeys the target probability distribution. We evaluate the performance of our approach through extensive simulations and experiments, and the results demonstrate the feasibility and effectiveness of the proposed approach.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0969-0974
Balanced Hashgraph Based on Dynamic MCMC: Efficient, Practical and Compatible
In a blockchain system based on the HashGraph consensus algorithm, picking a target server for block propagation is a key step. The traditional HashGraph blockchain system uses a completely random approach to pick the target server, which has the advantage of ensuring the security of the system and reducing the impact of attacks and single server failures received by the system. However, the random selection of target servers may lead to a situation where low performance servers are under high load but high performance servers are under load. In order to make each server process the block data with maximum performance, this paper proposes a balanced up-linking strategy, which calculates the server's reputation by evaluating the status of four dimensions, such as remaining performance, security, response time, and trustworthiness of the server, and then constructs a geometric probability model by Markov model and Monte Carlo method, so that the block is randomly propagated to each server with a specific probability according to the server status. In the process of running the blockchain system with this strategy, the probability of propagation to each server is dynamically adjusted according to the changing server status, so that the frequency distribution of all servers in the cluster receiving blocks obeys the target probability distribution. We evaluate the performance of our approach through extensive simulations and experiments, and the results demonstrate the feasibility and effectiveness of the proposed approach.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (11) , 13976-13983
Multi-Action Dialog Policy Learning from Logged User Feedback
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (11) , 13976-13983
Open AccessMulti-Action Dialog Policy Learning from Logged User Feedback
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.
- Open Access
- 26 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (1) , 1-24
An Effective and Differentially Private Protocol for Secure Distributed Cardinality Estimation
Counting the number of distinct elements distributed over multiple data holders is a fundamental problem with many real-world applications ranging from crowd counting to network monitoring. Although a number of space and computationally efficient sketch methods (e.g., the Flajolet-Martin sketch and the HyperLogLog sketch) for cardinality estimation have been proposed to solve the above problem, these sketch methods are insecure when considering privacy concerns related to the use of each data holder's personal dataset. Despite a recently proposed protocol that successfully implements the well-known Flajolet-Martin (FM) sketch on a secret-sharing based multiparty computation (MPC) framework for solving the problem of private distributed cardinality estimation (PDCE), we observe that this MPC-FM protocol is not differentially private. In addition, the MPC-FM protocol is computationally expensive, which limits its applications to data holders with limited computation resources. To address the above issues, in this paper we propose a novel protocol DP-DICE, which is computationally efficient and differentially private for solving the problem of PDCE. Experimental results show that our DP-DICE achieves orders of magnitude speedup and reduces the estimation error by several times in comparison with state-of-the-arts under the same security requirements.
- 26 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (1) , 1-24
Open AccessAn Effective and Differentially Private Protocol for Secure Distributed Cardinality Estimation
Counting the number of distinct elements distributed over multiple data holders is a fundamental problem with many real-world applications ranging from crowd counting to network monitoring. Although a number of space and computationally efficient sketch methods (e.g., the Flajolet-Martin sketch and the HyperLogLog sketch) for cardinality estimation have been proposed to solve the above problem, these sketch methods are insecure when considering privacy concerns related to the use of each data holder's personal dataset. Despite a recently proposed protocol that successfully implements the well-known Flajolet-Martin (FM) sketch on a secret-sharing based multiparty computation (MPC) framework for solving the problem of private distributed cardinality estimation (PDCE), we observe that this MPC-FM protocol is not differentially private. In addition, the MPC-FM protocol is computationally expensive, which limits its applications to data holders with limited computation resources. To address the above issues, in this paper we propose a novel protocol DP-DICE, which is computationally efficient and differentially private for solving the problem of PDCE. Experimental results show that our DP-DICE achieves orders of magnitude speedup and reduces the estimation error by several times in comparison with state-of-the-arts under the same security requirements.