Hao Niu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hao Niu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Chihiro Ono
KDDI Research, Inc., Fujimino, Japan
3 shared publications - Daichi Amagata
Graduate School of Information Science and Technology, The University of Osaka, Suita, Osaka, Japan
3 shared publications - Kei Yonekawa
KDDI Research, Inc
3 shared publications - Mori Kurokawa
KDDI Research, Inc
3 shared publications - Takahiro Hara
The University of Osaka
3 shared publications - Takuya Maekawa
The University of Osaka, Suita, Osaka, Japan
3 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12703-12714
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12703-12714
Open AccessCoarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 440-453
CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 440-453
Open AccessCartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1133-1144
Sample-Level Prototypical Federated Learning
With the increasing concerns about privacy and data regulations, federated learning (FL) has been emerging as a solution to train machine learning models collaboratively with non-exchangeable data from multiple clients. As a result of data locality, data is usually not identically or independently (non-IID) distributed across clients, and the non-IID property has long been the key challenge in FL. Furthermore, in real-world cross-silo scenarios, it is ubiquitous that clients are organizations owning private data from multiple domains internally, which exacerbates the non-IID issue. For example, in healthcare applications, each client (hospital) gathers data from patients with heterogeneous demographics. While previous works have made efforts to address the non-IID challenge across clients by assuming various relations among client-level data distributions and enabling personalized models at the client level, they ignore the internal data heterogeneity within each client or require explicit data domain indicators, which are hardly accessible in real-world data. Here, we propose Sample-Level Prototypical Federated Learning (SL-PFL) to bridge the gap. SL-PFL incorporates prototypical learning under the FL framework and provides a fine-grained personalized model for each data sample instead of learning one uniform model for all samples of each client. Meanwhile, it can be trained using data without ground-truth domain indicators. Experimental results demonstrate that our proposed method with sample-level personalized models outperforms existing FL methods with a global model or client-level personalized models on various real-world regression and classification tasks from weather, computer vision, and healthcare applications.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1133-1144
Sample-Level Prototypical Federated Learning
With the increasing concerns about privacy and data regulations, federated learning (FL) has been emerging as a solution to train machine learning models collaboratively with non-exchangeable data from multiple clients. As a result of data locality, data is usually not identically or independently (non-IID) distributed across clients, and the non-IID property has long been the key challenge in FL. Furthermore, in real-world cross-silo scenarios, it is ubiquitous that clients are organizations owning private data from multiple domains internally, which exacerbates the non-IID issue. For example, in healthcare applications, each client (hospital) gathers data from patients with heterogeneous demographics. While previous works have made efforts to address the non-IID challenge across clients by assuming various relations among client-level data distributions and enabling personalized models at the client level, they ignore the internal data heterogeneity within each client or require explicit data domain indicators, which are hardly accessible in real-world data. Here, we propose Sample-Level Prototypical Federated Learning (SL-PFL) to bridge the gap. SL-PFL incorporates prototypical learning under the FL framework and provides a fine-grained personalized model for each data sample instead of learning one uniform model for all samples of each client. Meanwhile, it can be trained using data without ground-truth domain indicators. Experimental results demonstrate that our proposed method with sample-level personalized models outperforms existing FL methods with a global model or client-level personalized models on various real-world regression and classification tasks from weather, computer vision, and healthcare applications.
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 37-45
User-irrelevant Cross-domain Association Analysis for Cross-domain Recommendation with Transfer Learning
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 37-45
Open AccessUser-irrelevant Cross-domain Association Analysis for Cross-domain Recommendation with Transfer Learning
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-23
Towards Multimodal Spatio-Temporal Transformer-based Models for Traffic Congestion Prediction
Robust predictions of traffic congestion play a crucial role in intelligent transportation systems. Recently, multimodal data have been applied to improve the performance of traffic congestion prediction models, such as rainfall, social network posts, incident reports, etc. In this paper, we attempt to use both dynamic people-flow and rainfall data, along with a transformer-based prediction model for traffic congestion prediction. We experiment an early fusion method for combining the multimodal data. Our experiments are conducted using two private datasets containing congestion and people-flow data, alongside a corresponding public dataset that provides rainfall data. The results indicate that incorporating the people-flow data into our prediction model enhances its performance.
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-23
Open AccessTowards Multimodal Spatio-Temporal Transformer-based Models for Traffic Congestion Prediction
Robust predictions of traffic congestion play a crucial role in intelligent transportation systems. Recently, multimodal data have been applied to improve the performance of traffic congestion prediction models, such as rainfall, social network posts, incident reports, etc. In this paper, we attempt to use both dynamic people-flow and rainfall data, along with a transformer-based prediction model for traffic congestion prediction. We experiment an early fusion method for combining the multimodal data. Our experiments are conducted using two private datasets containing congestion and people-flow data, alongside a corresponding public dataset that provides rainfall data. The results indicate that incorporating the people-flow data into our prediction model enhances its performance.
- Open Access
- 13 May 2019
- Published by Association for Computing Machinery (ACM)
- p. 361-366
Behavior Matching between Different Domains based on Canonical Correlation Analysis
- 13 May 2019
- Published by Association for Computing Machinery (ACM)
- p. 361-366
Open AccessBehavior Matching between Different Domains based on Canonical Correlation Analysis
- Open Access
- 13 May 2019
- Published by Association for Computing Machinery (ACM)
- p. 398-403
Preliminary Investigation of Alleviating User Cold-Start Problem in E-commerce with Deep Cross-Domain Recommender System
- 13 May 2019
- Published by Association for Computing Machinery (ACM)
- p. 398-403
Open AccessPreliminary Investigation of Alleviating User Cold-Start Problem in E-commerce with Deep Cross-Domain Recommender System