Tong Wang
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
Tong Wang has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Barrett W. Thomas
Department of Business Analytics, Tippie College of Business, University of Iowa, Iowa City, Iowa 52242
3 shared publications - Cynthia Rudin
Duke University, Durham, NC, USA
3 shared publications - Ronilo Ragodos
University of New Hampshire, Durham, New Hampshire, USA
3 shared publications Azeez Butali
Department of Oral Pathology, Radiology, and Medicine, University of Iowa, Iowa City, USA
2 shared publications- Boxiang Wang
Department of Statistics and Actuarial Science, The University of Iowa, Iowa City, Iowa 52242
2 shared publications - Brian J. Howe
The Iowa Institute for Oral Health Research, College of Dentistry, University of Iowa, Iowa City, USA
2 shared publications
Latest Publications
- 1 May 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (3) , 766-782
PIE—Partially Interpretable Estimators with Refinement
We propose a new form of predictive models, Partially Interpretable Estimators (PIE), which jointly train an interpretable model and a black-box model to achieve partial model transparency while maintaining high predictive performance. Our design is motivated by prior research showing that interpretability does not require exposing all model details. Therefore, our objective is to explain the main components of the prediction, withholding complicated calculations that may not be necessary for users. PIE is designed to attribute a prediction to the contribution from individual features via a sparse linear additive model to achieve interpretability while complementing the prediction with a black-box model to boost the predictive performance. As such, the linear additive model captures the primary feature contributions, while the black-box component augments PIE’s predictive power by capturing the “nuances” of feature interactions as a refinement. Moreover, we include a sparsity constraint, allowing users to adjust the model to meet domain-specific needs of interpretability. To optimize predictive performance, we propose a coordinated training algorithm that jointly trains the two components of PIE. Experimental results show that PIE achieves accuracy comparable to state-of-the-art black-box models, with human assessments confirming that its interpretability is nearly equivalent to linear models. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0098 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0098 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 1 May 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (3) , 766-782
PIE—Partially Interpretable Estimators with Refinement
We propose a new form of predictive models, Partially Interpretable Estimators (PIE), which jointly train an interpretable model and a black-box model to achieve partial model transparency while maintaining high predictive performance. Our design is motivated by prior research showing that interpretability does not require exposing all model details. Therefore, our objective is to explain the main components of the prediction, withholding complicated calculations that may not be necessary for users. PIE is designed to attribute a prediction to the contribution from individual features via a sparse linear additive model to achieve interpretability while complementing the prediction with a black-box model to boost the predictive performance. As such, the linear additive model captures the primary feature contributions, while the black-box component augments PIE’s predictive power by capturing the “nuances” of feature interactions as a refinement. Moreover, we include a sparsity constraint, allowing users to adjust the model to meet domain-specific needs of interpretability. To optimize predictive performance, we propose a coordinated training algorithm that jointly trains the two components of PIE. Experimental results show that PIE achieves accuracy comparable to state-of-the-art black-box models, with human assessments confirming that its interpretability is nearly equivalent to linear models. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0098 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0098 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 153-162
ConPro-GAIL: Interpretable Policy Learning via Conceptual Prototyping for Human Spatiotemporal Decision Understanding
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 153-162
Open AccessConPro-GAIL: Interpretable Policy Learning via Conceptual Prototyping for Human Spatiotemporal Decision Understanding
- 3 June 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for PIE - Partially Interpretable Estimators with Refinement
This repository implements a novel Partially Interpretable Model (PIE) framework introduced by Wang et al. arxiv:2105.02410. This framework jointly train an interpretable model and a black-box model to achieve high predictive performance as well as partial model transparency
- 3 June 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for PIE - Partially Interpretable Estimators with Refinement
This repository implements a novel Partially Interpretable Model (PIE) framework introduced by Wang et al. arxiv:2105.02410. This framework jointly train an interpretable model and a black-box model to achieve high predictive performance as well as partial model transparency
- Open Access
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Training keyphrase generation (KPG) models require a large amount of annotated data, which can be prohibitively expensive and often limited to specific domains. In this study, we first demonstrate that large distribution shifts among different domains severely hinder the transferability of KPG models. We then propose a three-stage pipeline, which gradually guides KPG models' learning focus from general syntactical features to domain-related semantics, in a data-efficient manner. With Domain-general Phrase pre-training, we pre-train Sequence-to-Sequence models with generic phrase annotations that are widely available on the web, which enables the models to generate phrases in a wide range of domains. The resulting model is then applied in the Transfer Labeling stage to produce domain-specific pseudo keyphrases, which help adapt models to a new domain. Finally, we fine-tune the model with limited data with true labels to fully adapt it to the target domain. Our experiment results show that the proposed process can produce good-quality keyphrases in new domains and achieve consistent improvements after adaptation with limited in-domain annotated data. All code and datasets are available at https://github.com/memray/OpenNMT-kpg-release.
Open AccessGeneral-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Training keyphrase generation (KPG) models require a large amount of annotated data, which can be prohibitively expensive and often limited to specific domains. In this study, we first demonstrate that large distribution shifts among different domains severely hinder the transferability of KPG models. We then propose a three-stage pipeline, which gradually guides KPG models' learning focus from general syntactical features to domain-related semantics, in a data-efficient manner. With Domain-general Phrase pre-training, we pre-train Sequence-to-Sequence models with generic phrase annotations that are widely available on the web, which enables the models to generate phrases in a wide range of domains. The resulting model is then applied in the Transfer Labeling stage to produce domain-specific pseudo keyphrases, which help adapt models to a new domain. Finally, we fine-tune the model with limited data with true labels to fully adapt it to the target domain. Our experiment results show that the proposed process can produce good-quality keyphrases in new domains and achieve consistent improvements after adaptation with limited in-domain annotated data. All code and datasets are available at https://github.com/memray/OpenNMT-kpg-release.
- Open Access
Learning to Advise Humans in High-Stakes Settings
Expert decision-makers (DMs) in high-stakes AI-assisted decision-making (AIaDM) settings receive and reconcile recommendations from AI systems before making their final decisions. We identify distinct properties of these settings which are key to developing AIaDM models that effectively benefit team performance. First, DMs incur reconciliation costs from exerting decision-making resources (e.g., time and effort) when reconciling AI recommendations that contradict their own judgment. Second, DMs in AIaDM settings exhibit algorithm discretion behavior (ADB), i.e., an idiosyncratic tendency to imperfectly accept or reject algorithmic recommendations for any given decision task. The human's reconciliation costs and imperfect discretion behavior introduce the need to develop AI systems which (1) provide recommendations selectively, (2) leverage the human partner's ADB to maximize the team's decision accuracy while regularizing for reconciliation costs, and (3) are inherently interpretable. We refer to the task of developing AI to advise humans in AIaDM settings as learning to advise and we address this task by first introducing the AI-assisted Team (AIaT)-Learning Framework. We instantiate our framework to develop TeamRules (TR): an algorithm that produces rule-based models and recommendations for AIaDM settings. TR is optimized to selectively advise a human and to trade-off reconciliation costs and team accuracy for a given environment by leveraging the human partner's ADB. Evaluations on synthetic and real-world benchmark datasets with a variety of simulated human accuracy and discretion behaviors show that TR robustly improves the team's objective across settings over interpretable, rule-based alternatives.
Open AccessLearning to Advise Humans in High-Stakes Settings
Expert decision-makers (DMs) in high-stakes AI-assisted decision-making (AIaDM) settings receive and reconcile recommendations from AI systems before making their final decisions. We identify distinct properties of these settings which are key to developing AIaDM models that effectively benefit team performance. First, DMs incur reconciliation costs from exerting decision-making resources (e.g., time and effort) when reconciling AI recommendations that contradict their own judgment. Second, DMs in AIaDM settings exhibit algorithm discretion behavior (ADB), i.e., an idiosyncratic tendency to imperfectly accept or reject algorithmic recommendations for any given decision task. The human's reconciliation costs and imperfect discretion behavior introduce the need to develop AI systems which (1) provide recommendations selectively, (2) leverage the human partner's ADB to maximize the team's decision accuracy while regularizing for reconciliation costs, and (3) are inherently interpretable. We refer to the task of developing AI to advise humans in AIaDM settings as learning to advise and we address this task by first introducing the AI-assisted Team (AIaT)-Learning Framework. We instantiate our framework to develop TeamRules (TR): an algorithm that produces rule-based models and recommendations for AIaDM settings. TR is optimized to selectively advise a human and to trade-off reconciliation costs and team accuracy for a given environment by leveraging the human partner's ADB. Evaluations on synthetic and real-world benchmark datasets with a variety of simulated human accuracy and discretion behaviors show that TR robustly improves the team's objective across settings over interpretable, rule-based alternatives.
- Open Access
ProtoX: Explaining a Reinforcement Learning Agent via Prototyping
While deep reinforcement learning has proven to be successful in solving control tasks, the "black-box" nature of an agent has received increasing concerns. We propose a prototype-based post-hoc policy explainer, ProtoX, that explains a blackbox agent by prototyping the agent's behaviors into scenarios, each represented by a prototypical state. When learning prototypes, ProtoX considers both visual similarity and scenario similarity. The latter is unique to the reinforcement learning context, since it explains why the same action is taken in visually different states. To teach ProtoX about visual similarity, we pre-train an encoder using contrastive learning via self-supervised learning to recognize states as similar if they occur close together in time and receive the same action from the black-box agent. We then add an isometry layer to allow ProtoX to adapt scenario similarity to the downstream task. ProtoX is trained via imitation learning using behavior cloning, and thus requires no access to the environment or agent. In addition to explanation fidelity, we design different prototype shaping terms in the objective function to encourage better interpretability. We conduct various experiments to test ProtoX. Results show that ProtoX achieved high fidelity to the original black-box agent while providing meaningful and understandable explanations.
Open AccessProtoX: Explaining a Reinforcement Learning Agent via Prototyping
While deep reinforcement learning has proven to be successful in solving control tasks, the "black-box" nature of an agent has received increasing concerns. We propose a prototype-based post-hoc policy explainer, ProtoX, that explains a blackbox agent by prototyping the agent's behaviors into scenarios, each represented by a prototypical state. When learning prototypes, ProtoX considers both visual similarity and scenario similarity. The latter is unique to the reinforcement learning context, since it explains why the same action is taken in visually different states. To teach ProtoX about visual similarity, we pre-train an encoder using contrastive learning via self-supervised learning to recognize states as similar if they occur close together in time and receive the same action from the black-box agent. We then add an isometry layer to allow ProtoX to adapt scenario similarity to the downstream task. ProtoX is trained via imitation learning using behavior cloning, and thus requires no access to the environment or agent. In addition to explanation fidelity, we design different prototype shaping terms in the objective function to encourage better interpretability. We conduct various experiments to test ProtoX. Results show that ProtoX achieved high fidelity to the original black-box agent while providing meaningful and understandable explanations.
- 1 November 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 34 (6) , 3259-3276
Disjunctive Rule Lists
In this study, we present an interpretable model, disjunctive rule list (DisRL) for regression. This research is motivated by the increasing need for model interpretability, especially in high-stakes decisions such as medicine, where decisions are made on or related to humans. DisRL is a generalized form of rule lists. A DisRL model consists of a list of disjunctive rules embedded in an if-else logic structure that stratifies the data space. Compared with traditional decision trees and other rule list models in the literature that stratify the feature space with single itemsets (an itemset is a conjunction of conditions), each disjunctive rule in DisRL uses a set of itemsets to collectively cover a subregion in the feature space. In addition, a DisRL model is constructed under a global objective that balances the predictive performance and model complexity. To train a DisRL model, we devise a hierarchical stochastic local search algorithm that exploits the properties of DisRL’s unique structure to improve search efficiency. The algorithm adopts the main structure of simulated annealing and customizes the proposing strategy for faster convergence. Meanwhile, the algorithm uses a prefix bound to locate a subset of the search area, effectively pruning the search space at each iteration. An ablation study shows the effectiveness of this strategy in pruning the search space. Experiments on public benchmark datasets demonstrate that DisRL outperforms baseline interpretable models, including decision trees and other rule-based regressors. History: Accepted by J. Paul Brooks, Area Editor for Applications in Biology, Medicine, & Healthcare. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplementary Information [ https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.1242 ] or is available from the IJOC GitHub software repository ( https://github.com/INFORMSJoC ) at [ http://dx.doi.org/10.5281/zenodo.6954927 ].
- 1 November 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 34 (6) , 3259-3276
Disjunctive Rule Lists
In this study, we present an interpretable model, disjunctive rule list (DisRL) for regression. This research is motivated by the increasing need for model interpretability, especially in high-stakes decisions such as medicine, where decisions are made on or related to humans. DisRL is a generalized form of rule lists. A DisRL model consists of a list of disjunctive rules embedded in an if-else logic structure that stratifies the data space. Compared with traditional decision trees and other rule list models in the literature that stratify the feature space with single itemsets (an itemset is a conjunction of conditions), each disjunctive rule in DisRL uses a set of itemsets to collectively cover a subregion in the feature space. In addition, a DisRL model is constructed under a global objective that balances the predictive performance and model complexity. To train a DisRL model, we devise a hierarchical stochastic local search algorithm that exploits the properties of DisRL’s unique structure to improve search efficiency. The algorithm adopts the main structure of simulated annealing and customizes the proposing strategy for faster convergence. Meanwhile, the algorithm uses a prefix bound to locate a subset of the search area, effectively pruning the search space at each iteration. An ablation study shows the effectiveness of this strategy in pruning the search space. Experiments on public benchmark datasets demonstrate that DisRL outperforms baseline interpretable models, including decision trees and other rule-based regressors. History: Accepted by J. Paul Brooks, Area Editor for Applications in Biology, Medicine, & Healthcare. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplementary Information [ https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.1242 ] or is available from the IJOC GitHub software repository ( https://github.com/INFORMSJoC ) at [ http://dx.doi.org/10.5281/zenodo.6954927 ].
- 23 September 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Disjunctive Rule Lists
This is the code for Disjunctive Rule Set, which is a rule-based model for classification.
- 23 September 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Disjunctive Rule Lists
This is the code for Disjunctive Rule Set, which is a rule-based model for classification.
- Open Access
- 8 August 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1
Author Correction: Dental anomaly detection using intraoral photos via deep learning
- 8 August 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1
Open AccessAuthor Correction: Dental anomaly detection using intraoral photos via deep learning
- Open Access
- 8 July 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-8
Dental anomaly detection using intraoral photos via deep learning
Children with orofacial clefting (OFC) present with a wide range of dental anomalies. Identifying these anomalies is vital to understand their etiology and to discern the complex phenotypic spectrum of OFC. Such anomalies are currently identified using intra-oral exams by dentists, a costly and time-consuming process. We claim that automating the process of anomaly detection using deep neural networks (DNNs) could increase efficiency and provide reliable anomaly detection while potentially increasing the speed of research discovery. This study characterizes the use of` DNNs to identify dental anomalies by training a DNN model using intraoral photographs from the largest international cohort to date of children with nonsyndromic OFC and controls (OFC1). In this project, the intraoral images were submitted to a Convolutional Neural Network model to perform multi-label multi-class classification of 10 dental anomalies. The network predicts whether an individual exhibits any of the 10 anomalies and can do so significantly faster than a human rater can. For all but three anomalies, F1 scores suggest that our model performs competitively at anomaly detection when compared to a dentist with 8 years of clinical experience. In addition, we use saliency maps to provide a post-hoc interpretation for our model’s predictions. This enables dentists to examine and verify our model’s predictions.
- 8 July 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-8
Open AccessDental anomaly detection using intraoral photos via deep learning
Children with orofacial clefting (OFC) present with a wide range of dental anomalies. Identifying these anomalies is vital to understand their etiology and to discern the complex phenotypic spectrum of OFC. Such anomalies are currently identified using intra-oral exams by dentists, a costly and time-consuming process. We claim that automating the process of anomaly detection using deep neural networks (DNNs) could increase efficiency and provide reliable anomaly detection while potentially increasing the speed of research discovery. This study characterizes the use of` DNNs to identify dental anomalies by training a DNN model using intraoral photographs from the largest international cohort to date of children with nonsyndromic OFC and controls (OFC1). In this project, the intraoral images were submitted to a Convolutional Neural Network model to perform multi-label multi-class classification of 10 dental anomalies. The network predicts whether an individual exhibits any of the 10 anomalies and can do so significantly faster than a human rater can. For all but three anomalies, F1 scores suggest that our model performs competitively at anomaly detection when compared to a dentist with 8 years of clinical experience. In addition, we use saliency maps to provide a post-hoc interpretation for our model’s predictions. This enables dentists to examine and verify our model’s predictions.