Tian Tian
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
Tian Tian has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Honglei Lin
School of Electrical Engineering, Heilongjiang University, Harbin, China
2 shared publications - Shuli Sun
Heilongjiang University
2 shared publications Tingsan Pan
College of Intelligence and Computing, Tianjin University, China
2 shared publications- Yuexian Hou
College of Intelligence and Computing Tianjin University Tianjin China
2 shared publications - Aihua Wang
School of Information and Electronics, Beijing Institute of Technology, Beijing, China
1 shared publication - Chunyan Miao
School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8547-8554
CATeye: Coupled Attribute–Topology Invariance Learning for Voucher Abuse Detection
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8547-8554
Open AccessCATeye: Coupled Attribute–Topology Invariance Learning for Voucher Abuse Detection
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2835-2846
FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2835-2846
Open AccessFreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
- Open Access
- 4 December 2021
- Published by Association for Computing Machinery (ACM)
- p. 323-330
Mining Latent Semantic Correlation inspired by Quantum Entanglement
Text representation learning is the cornerstone of solving downstream problems in Natural Language Processing (NLP). However, mining the potential explanatory factors or semantic associations behind data, rather than simply representing the superficial co-occurrence of words, remains a non-trivial challenge. To this end, we seek inspiration from the Quantum Entanglement (QE) which can effectively provide a complete description for the nature of realities and a globally-determined intrinsic correlation of considered objects, thus proposing a novel representation learning hypothesis called the Latent Semantic Correlation (LSC), namely the implicit internal coherence between the semantic space and its corresponding category space. To construct a multi-granularity representation from sememes to words, phrases, sentences, and higher-level LSC, we implement a QE-inspired Network (QEN) under the constraints of quantum formalism and propose the Local Semantic Measurement (LSM) and Extraction (LSE) for effectively capturing probability distribution information from the entangled state of a bipartite quantum system, which has a clear geometrical motivation but also supports a well-founded probabilistic interpretation. Experimental results conducted on several benchmarking classification tasks prove the validity of the LSC hypothesis and the superiority of QEN.
- 4 December 2021
- Published by Association for Computing Machinery (ACM)
- p. 323-330
Open AccessMining Latent Semantic Correlation inspired by Quantum Entanglement
Text representation learning is the cornerstone of solving downstream problems in Natural Language Processing (NLP). However, mining the potential explanatory factors or semantic associations behind data, rather than simply representing the superficial co-occurrence of words, remains a non-trivial challenge. To this end, we seek inspiration from the Quantum Entanglement (QE) which can effectively provide a complete description for the nature of realities and a globally-determined intrinsic correlation of considered objects, thus proposing a novel representation learning hypothesis called the Latent Semantic Correlation (LSC), namely the implicit internal coherence between the semantic space and its corresponding category space. To construct a multi-granularity representation from sememes to words, phrases, sentences, and higher-level LSC, we implement a QE-inspired Network (QEN) under the constraints of quantum formalism and propose the Local Semantic Measurement (LSM) and Extraction (LSE) for effectively capturing probability distribution information from the entangled state of a bipartite quantum system, which has a clear geometrical motivation but also supports a well-founded probabilistic interpretation. Experimental results conducted on several benchmarking classification tasks prove the validity of the LSC hypothesis and the superiority of QEN.
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 755-759
Modeling Semantic Inspired by Quantum Composite System
In the field of Natural Language Processing (NLP), especially for many specific tasks, representing and modeling semantic of text plays essential role. Generally speaking, by extracting feature of words, we can find the internal relationship between words and model text semantics. Further more, there have been achievements in using quantum concepts to construct language models, which suggests the effectiveness of applying quantum theory to semantic learning and representation. However, in the current research of quantum-inspired language model, semantic of the text is often directly modeled by quantum concept (e.g., density matrix), which blurs the original meaning of the word itself. In this study, we propose the composite semantic system (CSS) hypothesis and construct a quantum-inspired semantic representation network (QSRN). We apply QSRN to four different text classification tasks, the experimental results show the effectiveness of the algorithm and verify the hypothesis we proposed.
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 755-759
Modeling Semantic Inspired by Quantum Composite System
In the field of Natural Language Processing (NLP), especially for many specific tasks, representing and modeling semantic of text plays essential role. Generally speaking, by extracting feature of words, we can find the internal relationship between words and model text semantics. Further more, there have been achievements in using quantum concepts to construct language models, which suggests the effectiveness of applying quantum theory to semantic learning and representation. However, in the current research of quantum-inspired language model, semantic of the text is often directly modeled by quantum concept (e.g., density matrix), which blurs the original meaning of the word itself. In this study, we propose the composite semantic system (CSS) hypothesis and construct a quantum-inspired semantic representation network (QSRN). We apply QSRN to four different text classification tasks, the experimental results show the effectiveness of the algorithm and verify the hypothesis we proposed.
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3289-3294
Fusion Filtering for Stochastic Systems with Correlated Noises and Deception Attacks
This paper is concerned with fusion filtering problem for a class of stochastic systems subject to both correlated noises and deception attacks. The system noise and measurement noises of different sensors are cross-correlated at the same time instant. During the data transmission over network, the deception attack signals are injected randomly, whose statues are described by a group of Bernoulli variables. The centralized fusion filter is proposed via an innovation analysis approach. In order to improve robustness and reduce computational burden, a distributed fusion filter is put forward by using matrix-weighted fusion estimation algorithm in the linear unbiased minimum variance sense. A simulation example is given to show the effectiveness of the proposed algorithms.
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3289-3294
Fusion Filtering for Stochastic Systems with Correlated Noises and Deception Attacks
This paper is concerned with fusion filtering problem for a class of stochastic systems subject to both correlated noises and deception attacks. The system noise and measurement noises of different sensors are cross-correlated at the same time instant. During the data transmission over network, the deception attack signals are injected randomly, whose statues are described by a group of Bernoulli variables. The centralized fusion filter is proposed via an innovation analysis approach. In order to improve robustness and reduce computational burden, a distributed fusion filter is put forward by using matrix-weighted fusion estimation algorithm in the linear unbiased minimum variance sense. A simulation example is given to show the effectiveness of the proposed algorithms.
- Open Access
- 1 October 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1648 (3) , 032057
Research on the Innovation and Development of College English Education Integrating Network Technology in the Age of Media and Information
English is an important common language in the world nowadays. Based on the accelerating process of globalization, English language is becoming more and more important in the world. In recent years, China has paid more attention to college English education and achieved excellent results by adopting the corresponding teaching reform, which has improved college English teaching and students’ English level as a whole. However, there are still some problems in many colleges’ English teaching in China. Therefore, this article analyzes the impact of the integration of network technology in college English education in the era of media information on my country’s college English teaching, and puts forward some suggestions on the development and innovation of college English education in the era of media information.
- 1 October 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1648 (3) , 032057
Open AccessResearch on the Innovation and Development of College English Education Integrating Network Technology in the Age of Media and Information
English is an important common language in the world nowadays. Based on the accelerating process of globalization, English language is becoming more and more important in the world. In recent years, China has paid more attention to college English education and achieved excellent results by adopting the corresponding teaching reform, which has improved college English teaching and students’ English level as a whole. However, there are still some problems in many colleges’ English teaching in China. Therefore, this article analyzes the impact of the integration of network technology in college English education in the era of media information on my country’s college English teaching, and puts forward some suggestions on the development and innovation of college English education in the era of media information.
- 10 February 2020
- Published by Springer Nature in Science China Information Sciences
- Vol. 63 (3) , 1-3
Improved distinguisher search techniques based on parity sets
- 10 February 2020
- Published by Springer Nature in Science China Information Sciences
- Vol. 63 (3) , 1-3
Improved distinguisher search techniques based on parity sets
- Open Access
MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement learning agents. Much of the appeal comes from the fact that Atari games demonstrate aspects of competency we expect from an intelligent agent and are not biased toward any particular solution approach. The challenge of the ALE includes (1) the representation learning problem of extracting pertinent information from raw pixels, and (2) the behavioural learning problem of leveraging complex, delayed associations between actions and rewards. Often, the research questions we are interested in pertain more to the latter, but the representation learning problem adds significant computational expense. We introduce MinAtar, short for miniature Atari, a new set of environments that capture the general mechanics of specific Atari games while simplifying the representational complexity to focus more on the behavioural challenges. MinAtar consists of analogues of five Atari games: Seaquest, Breakout, Asterix, Freeway and Space Invaders. Each MinAtar environment provides the agent with a 10x10xn binary state representation. Each game plays out on a 10x10 grid with n channels corresponding to game-specific objects, such as ball, paddle and brick in the game Breakout. To investigate the behavioural challenges posed by MinAtar, we evaluated a smaller version of the DQN architecture as well as online actor-critic with eligibility traces. With the representation learning problem simplified, we can perform experiments with significantly less computational expense. In our experiments, we use the saved compute time to perform step-size parameter sweeps and more runs than is typical for the ALE. Experiments like this improve reproducibility, and allow us to draw more confident conclusions. We hope that MinAtar can allow researchers to thoroughly investigate behavioural challenges similar to those inherent in the ALE.
Open AccessMinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement learning agents. Much of the appeal comes from the fact that Atari games demonstrate aspects of competency we expect from an intelligent agent and are not biased toward any particular solution approach. The challenge of the ALE includes (1) the representation learning problem of extracting pertinent information from raw pixels, and (2) the behavioural learning problem of leveraging complex, delayed associations between actions and rewards. Often, the research questions we are interested in pertain more to the latter, but the representation learning problem adds significant computational expense. We introduce MinAtar, short for miniature Atari, a new set of environments that capture the general mechanics of specific Atari games while simplifying the representational complexity to focus more on the behavioural challenges. MinAtar consists of analogues of five Atari games: Seaquest, Breakout, Asterix, Freeway and Space Invaders. Each MinAtar environment provides the agent with a 10x10xn binary state representation. Each game plays out on a 10x10 grid with n channels corresponding to game-specific objects, such as ball, paddle and brick in the game Breakout. To investigate the behavioural challenges posed by MinAtar, we evaluated a smaller version of the DQN architecture as well as online actor-critic with eligibility traces. With the representation learning problem simplified, we can perform experiments with significantly less computational expense. In our experiments, we use the saved compute time to perform step-size parameter sweeps and more runs than is typical for the ALE. Experiments like this improve reproducibility, and allow us to draw more confident conclusions. We hope that MinAtar can allow researchers to thoroughly investigate behavioural challenges similar to those inherent in the ALE.
- 1 August 2017
- Published by Elsevier in Information Sciences
- Vol. 397-398, 118-136
State estimators for systems with random parameter matrices, stochastic nonlinearities, fading measurements and correlated noises
- 1 August 2017
- Published by Elsevier in Information Sciences
- Vol. 397-398, 118-136
State estimators for systems with random parameter matrices, stochastic nonlinearities, fading measurements and correlated noises
- Open Access
- 31 January 2015
- Published by Global Vision Press in International Journal of Multimedia and Ubiquitous Engineering
- Vol. 10 (1) , 149-158
Information Fusion Filter for Multi-rate Multi-sensor Systems
- 31 January 2015
- Published by Global Vision Press in International Journal of Multimedia and Ubiquitous Engineering
- Vol. 10 (1) , 149-158
Open AccessInformation Fusion Filter for Multi-rate Multi-sensor Systems