Handong Zhao
Research Subjects
Handong Zhao has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Ryan Anthony Rossi
Adobe Research, San Jose, USA
4 shared publications - Sungchul Kim
Institute for Global Rare Disease Network, Professional Graduate School of Korean Medicine, Wonkwang University, Iksan 54538, Republic of Korea
3 shared publications - Sheng Li
University of Virginia, Charlottesville, Virginia, USA
2 shared publications - Tong Yu
Adobe Research, San Jose, CA, USA
2 shared publications Yun Fu
Department of Electrical and Computer Engineering and College of Computer and Information Science, Northeastern Univeristy, Boston, MA, USA
2 shared publications- Zhengming Ding
Tulane University, New Orleans, USA
2 shared publications
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 663-672
Few-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 663-672
Open AccessFew-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 313-321
Interactive Visualization Recommendation with Hier-SUCB
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 313-321
Open AccessInteractive Visualization Recommendation with Hier-SUCB
- Open Access
- 11 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (3) , 1-41
Evaluation-free Time-series Forecasting Model Selection via Meta-learning
Time-series forecasting models are invariably used in a variety of domains for crucial decision-making. Traditionally these models are constructed by experts with considerable manual effort. Unfortunately, this approach has poor scalability while generating accurate forecasts for new datasets belonging to diverse applications. Without access to skilled domain-knowledge, one approach is to train all the models on the new time-series data and then select the best one. However, this approach is nonviable in practice. In this work, we develop techniques for fast automatic selection of the best forecasting model for a new unseen time-series dataset, without having to first train (or evaluate) all the models on the new time-series data to select the best one. In particular, we develop a forecasting meta-learning approach called AutoForecast that allows for the quick inference of the best time-series forecasting model for an unseen dataset. Our approach learns both forecasting models’ performances over time horizon of the same dataset and task similarity across different datasets. The experiments demonstrate the effectiveness of the approach over state-of-the-art (SOTA) single and ensemble methods and several SOTA meta-learners (adapted to our problem) in terms of selecting better forecasting models (i.e., 2 \(\times\) gain) for unseen tasks for univariate and multivariate testbeds. AutoForecast has also significant reduction in inference time compared to the naïve approach (doing inference using all possible models and then selecting the best one), with median of 42 \(\times\) across the two testbeds. We release our meta-learning database corpus (348 datasets), performances of the 322 forecasting models on the database corpus, meta-features, and source codes for the community to access them for forecasting model selection and to build on them with new datasets and models which can help advance automating time-series forecasting problem. In our released database corpus, we unveil new traces of Adobe computing cluster usage for production workloads.- 11 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (3) , 1-41
Open AccessEvaluation-free Time-series Forecasting Model Selection via Meta-learning
Time-series forecasting models are invariably used in a variety of domains for crucial decision-making. Traditionally these models are constructed by experts with considerable manual effort. Unfortunately, this approach has poor scalability while generating accurate forecasts for new datasets belonging to diverse applications. Without access to skilled domain-knowledge, one approach is to train all the models on the new time-series data and then select the best one. However, this approach is nonviable in practice. In this work, we develop techniques for fast automatic selection of the best forecasting model for a new unseen time-series dataset, without having to first train (or evaluate) all the models on the new time-series data to select the best one. In particular, we develop a forecasting meta-learning approach called AutoForecast that allows for the quick inference of the best time-series forecasting model for an unseen dataset. Our approach learns both forecasting models’ performances over time horizon of the same dataset and task similarity across different datasets. The experiments demonstrate the effectiveness of the approach over state-of-the-art (SOTA) single and ensemble methods and several SOTA meta-learners (adapted to our problem) in terms of selecting better forecasting models (i.e., 2 \(\times\) gain) for unseen tasks for univariate and multivariate testbeds. AutoForecast has also significant reduction in inference time compared to the naïve approach (doing inference using all possible models and then selecting the best one), with median of 42 \(\times\) across the two testbeds. We release our meta-learning database corpus (348 datasets), performances of the 322 forecasting models on the database corpus, meta-features, and source codes for the community to access them for forecasting model selection and to build on them with new datasets and models which can help advance automating time-series forecasting problem. In our released database corpus, we unveil new traces of Adobe computing cluster usage for production workloads. - Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-23
SpotLight: Visual Insight Recommendation
Visualization recommendation systems make understanding data more accessible to users of all skill levels by automatically generating visualizations for users to explore. However, most existing visualization recommendation systems focus on ranking all possible visualizations based on the attributes or encodings, which makes it difficult to find the most relevant insights. We therefore introduce a novel class of insight-based visualization recommendation systems that automatically rank and recommend groups of related insights as well as the most important insights within each group. Our approach combines results from different learning-based methods to discover insights automatically and generalizes to a variety of attribute types (e.g., categorical, numerical, and temporal), including non-trivial combinations of these attribute types. To demonstrate the utility of this approach, we implemented a insight-centric visualization recommendation system, SpotLight, and conducted a user study with twelve participants, which showed that users are able to quickly find and understand relevant insights in unfamiliar data.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-23
Open AccessSpotLight: Visual Insight Recommendation
Visualization recommendation systems make understanding data more accessible to users of all skill levels by automatically generating visualizations for users to explore. However, most existing visualization recommendation systems focus on ranking all possible visualizations based on the attributes or encodings, which makes it difficult to find the most relevant insights. We therefore introduce a novel class of insight-based visualization recommendation systems that automatically rank and recommend groups of related insights as well as the most important insights within each group. Our approach combines results from different learning-based methods to discover insights automatically and generalizes to a variety of attribute types (e.g., categorical, numerical, and temporal), including non-trivial combinations of these attribute types. To demonstrate the utility of this approach, we implemented a insight-centric visualization recommendation system, SpotLight, and conducted a user study with twelve participants, which showed that users are able to quickly find and understand relevant insights in unfamiliar data.
- Open Access
Hierarchical Conversational Preference Elicitation with Bandit Feedback
The recent advances of conversational recommendations provide a promising way to efficiently elicit users' preferences via conversational interactions. To achieve this, the recommender system conducts conversations with users, asking their preferences for different items or item categories. Most existing conversational recommender systems for cold-start users utilize a multi-armed bandit framework to learn users' preference in an online manner. However, they rely on a pre-defined conversation frequency for asking about item categories instead of individual items, which may incur excessive conversational interactions that hurt user experience. To enable more flexible questioning about key-terms, we formulate a new conversational bandit problem that allows the recommender system to choose either a key-term or an item to recommend at each round and explicitly models the rewards of these actions. This motivates us to handle a new exploration-exploitation (EE) trade-off between key-term asking and item recommendation, which requires us to accurately model the relationship between key-term and item rewards. We conduct a survey and analyze a real-world dataset to find that, unlike assumptions made in prior works, key-term rewards are mainly affected by rewards of representative items. We propose two bandit algorithms, Hier-UCB and Hier-LinUCB, that leverage this observed relationship and the hierarchical structure between key-terms and items to efficiently learn which items to recommend. We theoretically prove that our algorithm can reduce the regret bound's dependency on the total number of items from previous work. We validate our proposed algorithms and regret bound on both synthetic and real-world data.
Open AccessHierarchical Conversational Preference Elicitation with Bandit Feedback
The recent advances of conversational recommendations provide a promising way to efficiently elicit users' preferences via conversational interactions. To achieve this, the recommender system conducts conversations with users, asking their preferences for different items or item categories. Most existing conversational recommender systems for cold-start users utilize a multi-armed bandit framework to learn users' preference in an online manner. However, they rely on a pre-defined conversation frequency for asking about item categories instead of individual items, which may incur excessive conversational interactions that hurt user experience. To enable more flexible questioning about key-terms, we formulate a new conversational bandit problem that allows the recommender system to choose either a key-term or an item to recommend at each round and explicitly models the rewards of these actions. This motivates us to handle a new exploration-exploitation (EE) trade-off between key-term asking and item recommendation, which requires us to accurately model the relationship between key-term and item rewards. We conduct a survey and analyze a real-world dataset to find that, unlike assumptions made in prior works, key-term rewards are mainly affected by rewards of representative items. We propose two bandit algorithms, Hier-UCB and Hier-LinUCB, that leverage this observed relationship and the hierarchical structure between key-terms and items to efficiently learn which items to recommend. We theoretically prove that our algorithm can reduce the regret bound's dependency on the total number of items from previous work. We validate our proposed algorithms and regret bound on both synthetic and real-world data.
- Open Access
- 28 June 2022
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 36 (11) , 13035-13036
XDC: Adversarial Adaptive Cross Domain Face Clustering (Student Abstract)
In this work we propose a scheme, called XDC, that uses adversarial learning to train an adaptive cross domain clustering model. XDC trains a classifier on a labeled dataset and assigns labels to an unlabeled dataset. We benefit from adversarial learning such that the target dataset takes part in the training. We also use an existing image classifiers in a plug-and-play fashion (i.e, it can be replaced with any other image classifier). Unlike existing works we update the parameters of the encoder and expose the target dataset to the model during training. We apply our model on two face dataset and one non-face dataset and obtain comparable results with state-of-the-art face clustering models.
- 28 June 2022
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 36 (11) , 13035-13036
Open AccessXDC: Adversarial Adaptive Cross Domain Face Clustering (Student Abstract)
In this work we propose a scheme, called XDC, that uses adversarial learning to train an adaptive cross domain clustering model. XDC trains a classifier on a labeled dataset and assigns labels to an unlabeled dataset. We benefit from adversarial learning such that the target dataset takes part in the training. We also use an existing image classifiers in a plug-and-play fashion (i.e, it can be replaced with any other image classifier). Unlike existing works we update the parameters of the encoder and expose the target dataset to the model during training. We apply our model on two face dataset and one non-face dataset and obtain comparable results with state-of-the-art face clustering models.
- Open Access
Learnable Subspace Clustering
This paper studies the large-scale subspace clustering (LSSC) problem with million data points. Many popular subspace clustering methods cannot directly handle the LSSC problem although they have been considered as state-of-the-art methods for small-scale data points. A basic reason is that these methods often choose all data points as a big dictionary to build huge coding models, which results in a high time and space complexity. In this paper, we develop a learnable subspace clustering paradigm to efficiently solve the LSSC problem. The key idea is to learn a parametric function to partition the high-dimensional subspaces into their underlying low-dimensional subspaces instead of the expensive costs of the classical coding models. Moreover, we propose a unified robust predictive coding machine (RPCM) to learn the parametric function, which can be solved by an alternating minimization algorithm. In addition, we provide a bounded contraction analysis of the parametric function. To the best of our knowledge, this paper is the first work to efficiently cluster millions of data points among the subspace clustering methods. Experiments on million-scale datasets verify that our paradigm outperforms the related state-of-the-art methods in both efficiency and effectiveness.
Open AccessLearnable Subspace Clustering
This paper studies the large-scale subspace clustering (LSSC) problem with million data points. Many popular subspace clustering methods cannot directly handle the LSSC problem although they have been considered as state-of-the-art methods for small-scale data points. A basic reason is that these methods often choose all data points as a big dictionary to build huge coding models, which results in a high time and space complexity. In this paper, we develop a learnable subspace clustering paradigm to efficiently solve the LSSC problem. The key idea is to learn a parametric function to partition the high-dimensional subspaces into their underlying low-dimensional subspaces instead of the expensive costs of the classical coding models. Moreover, we propose a unified robust predictive coding machine (RPCM) to learn the parametric function, which can be solved by an alternating minimization algorithm. In addition, we provide a bounded contraction analysis of the parametric function. To the best of our knowledge, this paper is the first work to efficiently cluster millions of data points among the subspace clustering methods. Experiments on million-scale datasets verify that our paradigm outperforms the related state-of-the-art methods in both efficiency and effectiveness.
- Open Access
- 20 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 27 (1) , 236-248
Consensus Regularized Multi-View Outlier Detection
Identifying different types of data outliers with abnormal behaviors in multi-view data setting is challenging due to the complicated data distributions across different views. Conventional approaches achieve this by learning a new latent feature representation with the pairwise constraint on different view data. In this paper, we argue that the existing methods are expensive in generalizing their models from two-view data to three-view (or more) data, in terms of the number of introduced variables and detection performance. To address this, we propose a novel multi-view outlier detection method with consensus regularization on the latent representations. Specifically, we explicitly characterize each kind of outliers by the intrinsic cluster assignment labels and sample-specific errors. Moreover, we make a thorough discussion about the proposed consensus-regularization and the pairwise-regularization. Correspondingly, an optimization solution based on augmented Lagrangian multiplier method is proposed and derived in details. In the experiments, we evaluate our method on five well-known machine learning data sets with different outlier settings. Further, to show its effectiveness in real-world computer vision scenario, we tailor our proposed model to saliency detection and face reconstruction applications. The extensive results of both standard multi-view outlier detection task and the extended computer vision tasks demonstrate the effectiveness of our proposed method.
- 20 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 27 (1) , 236-248
Open AccessConsensus Regularized Multi-View Outlier Detection
Identifying different types of data outliers with abnormal behaviors in multi-view data setting is challenging due to the complicated data distributions across different views. Conventional approaches achieve this by learning a new latent feature representation with the pairwise constraint on different view data. In this paper, we argue that the existing methods are expensive in generalizing their models from two-view data to three-view (or more) data, in terms of the number of introduced variables and detection performance. To address this, we propose a novel multi-view outlier detection method with consensus regularization on the latent representations. Specifically, we explicitly characterize each kind of outliers by the intrinsic cluster assignment labels and sample-specific errors. Moreover, we make a thorough discussion about the proposed consensus-regularization and the pairwise-regularization. Correspondingly, an optimization solution based on augmented Lagrangian multiplier method is proposed and derived in details. In the experiments, we evaluate our method on five well-known machine learning data sets with different outlier settings. Further, to show its effectiveness in real-world computer vision scenario, we tailor our proposed model to saliency detection and face reconstruction applications. The extensive results of both standard multi-view outlier detection task and the extended computer vision tasks demonstrate the effectiveness of our proposed method.
- 3 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (7) , 1526-1539
Ensemble Subspace Segmentation Under Blockwise Constraints
The graph-based subspace segmentation technique has garnered a lot of attention in the visual data representation problem. In general, data (e.g., tracks of moving objects) are drawn from multiple linear subspaces. Thus, how to build a block-diagonal affinity matrix is the critical problem. In this paper, we propose a novel graph-based method, Ensemble Subspace Segmentation under Blockwise constraints (ESSB), which unifies least squares regression and a locality preserving graph regularizer into an ensemble learning framework. Specifically, compact encoding using least squares regression coefficients helps achieve a block-diagonal representation matrix among all samples. Meanwhile, the locality preserving regularizer tends to capture the intrinsic local structure, which further enhances the block-diagonal property. Both the blockwise efforts, i.e., least squares regression and the sparse regularizer, work jointly and are formulated in the ensemble learning framework, making ESSB more robust and efficient, especially when handling high-dimensional data. Finally, an efficient optimization solution based on inexact augmented Lagrange multiplier is derived with theoretical time complexity analysis. To demonstrate the effectiveness of the proposed method, we consider three different applications: face clustering, object clustering, and motion segmentation. Extensive results of both accuracy and normalized mutual information on four benchmarks, i.e., YaleB, ORL, COIL and Hopkins155, are reported. Also, the evaluations of computational cost are provided, based on which the superiority of our proposed method in both accuracy and efficiency is demonstrated compared with 12 baseline algorithms.
- 3 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (7) , 1526-1539
Ensemble Subspace Segmentation Under Blockwise Constraints
The graph-based subspace segmentation technique has garnered a lot of attention in the visual data representation problem. In general, data (e.g., tracks of moving objects) are drawn from multiple linear subspaces. Thus, how to build a block-diagonal affinity matrix is the critical problem. In this paper, we propose a novel graph-based method, Ensemble Subspace Segmentation under Blockwise constraints (ESSB), which unifies least squares regression and a locality preserving graph regularizer into an ensemble learning framework. Specifically, compact encoding using least squares regression coefficients helps achieve a block-diagonal representation matrix among all samples. Meanwhile, the locality preserving regularizer tends to capture the intrinsic local structure, which further enhances the block-diagonal property. Both the blockwise efforts, i.e., least squares regression and the sparse regularizer, work jointly and are formulated in the ensemble learning framework, making ESSB more robust and efficient, especially when handling high-dimensional data. Finally, an efficient optimization solution based on inexact augmented Lagrange multiplier is derived with theoretical time complexity analysis. To demonstrate the effectiveness of the proposed method, we consider three different applications: face clustering, object clustering, and motion segmentation. Extensive results of both accuracy and normalized mutual information on four benchmarks, i.e., YaleB, ORL, COIL and Hopkins155, are reported. Also, the evaluations of computational cost are provided, based on which the superiority of our proposed method in both accuracy and efficiency is demonstrated compared with 12 baseline algorithms.