Wenhe Liu
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
Wenhe Liu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Alexander G. Hauptmann
Carnegie Mellon University
3 shared publications - Yi Yang
Zhejiang University, China
3 shared publications Alexander G. Hauptmann
Language Technologies Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania
2 shared publications- Lijun Yu
Carnegie Mellon University
2 shared publications Ling Chen
Centre for Artificial Intelligence, University of Technology Sydney, Sydney, NSW, Australia
2 shared publicationsXiaojun Chang
Carnegie Mellon University, Pennsylvania, USA
2 shared publications
Latest Publications
- Open Access
Symmetry-Aware Transformers for Asymmetric Causal Discovery in Financial Time Series
Financial markets exhibit fundamental asymmetries in temporal causality, where policy interventions create asymmetric transmission patterns that traditional symmetric modeling approaches fail to capture. This work introduces a mathematical framework that exploits the inherent symmetries of transformer architectures while preserving essential asymmetric temporal relationships in financial causal inference. We develop CausalFormer, a symmetry-aware neural architecture that maintains the permutation equivariance properties of self-attention mechanisms while enforcing strict temporal asymmetry constraints for causal discovery. The framework incorporates three mathematically principled components: (1) a symmetric attention matrix construction with asymmetric temporal masking that preserves the mathematical elegance of transformer operations while ensuring causal consistency, (2) a multi-scale convolution module with symmetric kernel initialization but asymmetric temporal receptive fields that captures policy transmission effects across heterogeneous time horizons, and (3) enhanced Nelson–Siegel decomposition that maintains the symmetric factor structure while modeling the evolution dynamics of asymmetric factors. Our mathematical formulation establishes the formal symmetry properties of the attention mechanism under temporal transformations while proving asymmetric convergence behaviors in policy transmission scenarios. The integration of symmetric optimization landscapes with asymmetric causal constraints enables simultaneous achievement of mathematical elegance and economic interpretability. Comprehensive experiments on monetary policy datasets demonstrate that the symmetry-aware design achieves a 15.3% improvement in the accuracy of causal effect estimations and a 12.7% enhancement in the predictive performance compared to those for existing methods while maintaining 91.2% causal consistency scores. The framework successfully identifies asymmetric policy transmission mechanisms, revealing that monetary tightening exhibits 40% faster propagation than easing policies, establishing new mathematical insights into the temporal asymmetries in financial systems. This work demonstrates how principled exploitation of architectural symmetries combined with domain-specific asymmetric constraints opens up new directions for mathematically rigorous yet economically interpretable deep learning in financial econometrics, with broad applications spanning computational finance, economic forecasting, and policy analysis.
Open AccessSymmetry-Aware Transformers for Asymmetric Causal Discovery in Financial Time Series
Financial markets exhibit fundamental asymmetries in temporal causality, where policy interventions create asymmetric transmission patterns that traditional symmetric modeling approaches fail to capture. This work introduces a mathematical framework that exploits the inherent symmetries of transformer architectures while preserving essential asymmetric temporal relationships in financial causal inference. We develop CausalFormer, a symmetry-aware neural architecture that maintains the permutation equivariance properties of self-attention mechanisms while enforcing strict temporal asymmetry constraints for causal discovery. The framework incorporates three mathematically principled components: (1) a symmetric attention matrix construction with asymmetric temporal masking that preserves the mathematical elegance of transformer operations while ensuring causal consistency, (2) a multi-scale convolution module with symmetric kernel initialization but asymmetric temporal receptive fields that captures policy transmission effects across heterogeneous time horizons, and (3) enhanced Nelson–Siegel decomposition that maintains the symmetric factor structure while modeling the evolution dynamics of asymmetric factors. Our mathematical formulation establishes the formal symmetry properties of the attention mechanism under temporal transformations while proving asymmetric convergence behaviors in policy transmission scenarios. The integration of symmetric optimization landscapes with asymmetric causal constraints enables simultaneous achievement of mathematical elegance and economic interpretability. Comprehensive experiments on monetary policy datasets demonstrate that the symmetry-aware design achieves a 15.3% improvement in the accuracy of causal effect estimations and a 12.7% enhancement in the predictive performance compared to those for existing methods while maintaining 91.2% causal consistency scores. The framework successfully identifies asymmetric policy transmission mechanisms, revealing that monetary tightening exhibits 40% faster propagation than easing policies, establishing new mathematical insights into the temporal asymmetries in financial systems. This work demonstrates how principled exploitation of architectural symmetries combined with domain-specific asymmetric constraints opens up new directions for mathematically rigorous yet economically interpretable deep learning in financial econometrics, with broad applications spanning computational finance, economic forecasting, and policy analysis.
- 28 October 2022
- Published by Springer Nature
- p. 104-120
Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
- 28 October 2022
- Published by Springer Nature
- p. 104-120
Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
- Open Access
Training-free Monocular 3D Event Detection System for Traffic Surveillance
We focus on the problem of detecting traffic events in a surveillance scenario, including the detection of both vehicle actions and traffic collisions. Existing event detection systems are mostly learning-based and have achieved convincing performance when a large amount of training data is available. However, in real-world scenarios, collecting sufficient labeled training data is expensive and sometimes impossible (e.g. for traffic collision detection). Moreover, the conventional 2D representation of surveillance views is easily affected by occlusions and different camera views in nature. To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance. Our system firstly projects the vehicles into the 3D Euclidean space and estimates their kinematic states. Then we develop multiple simple yet effective ways to identify the events based on the kinematic patterns, which need no further training. Consequently, our system is robust to the occlusions and the viewpoint changes. Exclusive experiments report the superior result of our method on large-scale real-world surveillance datasets, which validates the effectiveness of our proposed system.
Open AccessTraining-free Monocular 3D Event Detection System for Traffic Surveillance
We focus on the problem of detecting traffic events in a surveillance scenario, including the detection of both vehicle actions and traffic collisions. Existing event detection systems are mostly learning-based and have achieved convincing performance when a large amount of training data is available. However, in real-world scenarios, collecting sufficient labeled training data is expensive and sometimes impossible (e.g. for traffic collision detection). Moreover, the conventional 2D representation of surveillance views is easily affected by occlusions and different camera views in nature. To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance. Our system firstly projects the vehicles into the 3D Euclidean space and estimates their kinematic states. Then we develop multiple simple yet effective ways to identify the events based on the kinematic patterns, which need no further training. Consequently, our system is robust to the occlusions and the viewpoint changes. Exclusive experiments report the superior result of our method on large-scale real-world surveillance datasets, which validates the effectiveness of our proposed system.
- Open Access
- 27 January 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 11 (2) , 1-15
Pair-based Uncertainty and Diversity Promoting Early Active Learning for Person Re-identification
The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging and practical problem called Early Active Learning, which is applied to the early stage of experiments when there is no pre-labeled sample available as references for human annotating. Previous early active learning methods suffer from two limitations for Re-ID. First, these instance-based algorithms select instances rather than pairs, which can result in missing optimal pairs for Re-ID. Second, most of these methods only consider the representativeness of instances, which can result in selecting less diverse and less informative pairs. To overcome these limitations, we propose a novel pair-based active learning for Re-ID. Our algorithm selects pairs instead of instances from the entire dataset for annotation. Besides representativeness, we further take into account the uncertainty and the diversity in terms of pairwise relations. Therefore, our algorithm can produce the most representative, informative, and diverse pairs for Re-ID data annotation. Extensive experimental results on five benchmark Re-ID datasets have demonstrated the superiority of the proposed pair-based early active learning algorithm.
- 27 January 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 11 (2) , 1-15
Open AccessPair-based Uncertainty and Diversity Promoting Early Active Learning for Person Re-identification
The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging and practical problem called Early Active Learning, which is applied to the early stage of experiments when there is no pre-labeled sample available as references for human annotating. Previous early active learning methods suffer from two limitations for Re-ID. First, these instance-based algorithms select instances rather than pairs, which can result in missing optimal pairs for Re-ID. Second, most of these methods only consider the representativeness of instances, which can result in selecting less diverse and less informative pairs. To overcome these limitations, we propose a novel pair-based active learning for Re-ID. Our algorithm selects pairs instead of instances from the entire dataset for annotation. Besides representativeness, we further take into account the uncertainty and the diversity in terms of pairwise relations. Therefore, our algorithm can produce the most representative, informative, and diverse pairs for Re-ID data annotation. Extensive experimental results on five benchmark Re-ID datasets have demonstrated the superiority of the proposed pair-based early active learning algorithm.
- 8 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 32 (7) , 1393-1404
Learning Distilled Graph for Large-Scale Social Network Data Clustering
Spectral analysis is critical in social network analysis. As a vital step of the spectral analysis, the graph construction in many existing works utilizes content data only. Unfortunately, the content data often consists of noisy, sparse, and redundant features, which makes the resulting graph unstable and unreliable. In practice, besides the content data, social networks also contain link information, which provides additional information for graph construction. Some of previous works utilize the link data. However, the link data is often incomplete, which makes the resulting graph incomplete. To address these issues, we propose a Distilled Graph Clustering (DGC) method. It pursuits a distilled graph based on both the content data and the link data. The proposed algorithm alternates between two steps: in the feature selection step, it finds the most representative feature subset w.r.t. an intermediate graph initialized with link data; in graph distillation step, the proposed method updates and refines the graph based on only the selected features. The final resulting graph, which is referred to as the distilled graph, is then utilized for spectral clustering on the large-scale social network data. Extensive experiments demonstrate the superiority of the proposed method.
- 8 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 32 (7) , 1393-1404
Learning Distilled Graph for Large-Scale Social Network Data Clustering
Spectral analysis is critical in social network analysis. As a vital step of the spectral analysis, the graph construction in many existing works utilizes content data only. Unfortunately, the content data often consists of noisy, sparse, and redundant features, which makes the resulting graph unstable and unreliable. In practice, besides the content data, social networks also contain link information, which provides additional information for graph construction. Some of previous works utilize the link data. However, the link data is often incomplete, which makes the resulting graph incomplete. To address these issues, we propose a Distilled Graph Clustering (DGC) method. It pursuits a distilled graph based on both the content data and the link data. The proposed algorithm alternates between two steps: in the feature selection step, it finds the most representative feature subset w.r.t. an intermediate graph initialized with link data; in graph distillation step, the proposed method updates and refines the graph based on only the selected features. The final resulting graph, which is referred to as the distilled graph, is then utilized for spectral clustering on the large-scale social network data. Extensive experiments demonstrate the superiority of the proposed method.
- Open Access
- 29 October 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 9 (6) , 1-20
Few-Shot Text and Image Classification via Analogical Transfer Learning
Learning from very few samples is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.
- 29 October 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 9 (6) , 1-20
Open AccessFew-Shot Text and Image Classification via Analogical Transfer Learning
Learning from very few samples is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.
- 8 January 2018
- Published by Springer Nature in Journal of Superconductivity and Novel Magnetism
- Vol. 31 (9) , 2811-2816
Effect of Heat Treatment on Microstructure and Magnetic Properties of Ce-Doped NdFeB Ribbons
- 8 January 2018
- Published by Springer Nature in Journal of Superconductivity and Novel Magnetism
- Vol. 31 (9) , 2811-2816
Effect of Heat Treatment on Microstructure and Magnetic Properties of Ce-Doped NdFeB Ribbons
- 30 December 2017
- Published by Springer Nature
- p. 103-118
Early Active Learning with Pairwise Constraint for Person Re-identification
- 30 December 2017
- Published by Springer Nature
- p. 103-118
Early Active Learning with Pairwise Constraint for Person Re-identification
- 20 September 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (3) , 3553-3577
Robust dictionary learning with graph regularization for unsupervised person re-identification
- 20 September 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (3) , 3553-3577
Robust dictionary learning with graph regularization for unsupervised person re-identification