Xiaojing Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaojing Du has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Andres Mauricio Cifuentes-Bernal
Adelaide University, Adelaide, Australia
1 shared publication - Debo Cheng
School of Computer Science and Technology, Hainan University, Haikou, Hainan, China
1 shared publication - Huijun Wang
School of Computer, Electronics Information, Guangxi University, Nanning, China
1 shared publication - Jianfeng Deng
School of Computer, Electronics and Information, Guangxi University, Nanning, China
1 shared publication - Jiuyong Li
Adelaide University
1 shared publication - Lin Liu
Adelaide University
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8840-8850
Energy-Efficient Training-Free Zero-Inflation Correction for Rainfall Forecasting with Time-Series Foundation Models
Accurate rainfall forecasting is essential for climate and disaster management, but precipitation exhibits extreme zero inflation that modern time-series Foundation Models (TSFMs) fundamentally cannot represent due to their continuous regression outputs. This structural mismatch causes pervasive drizzle-like false alarms, miscalibrated nonzero intensities, and severely underdetected extremes, while retraining large TSFMs is computationally prohibitive and environmentally unsustainable for most regions. We present a training-free wrapper that corrects zero inflation for frozen TSFMs without updating any parameters. Our method restores discrete zero mass using empirical occurrence statistics, aligns positive-value distributions via probability-integral transforms, and applies Generalized Pareto tail mapping for extreme-value consistency. Experiments on South Australian rainfall show substantial gains with negligible overhead (<5,ms per forecast, compared to hundreds of GPU-hours for retraining). The proposed wrapper enables carbon-neutral, globally deployable climate services and directly advances the goals of UN SDG~13 (Climate Action).
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8840-8850
Open AccessEnergy-Efficient Training-Free Zero-Inflation Correction for Rainfall Forecasting with Time-Series Foundation Models
Accurate rainfall forecasting is essential for climate and disaster management, but precipitation exhibits extreme zero inflation that modern time-series Foundation Models (TSFMs) fundamentally cannot represent due to their continuous regression outputs. This structural mismatch causes pervasive drizzle-like false alarms, miscalibrated nonzero intensities, and severely underdetected extremes, while retraining large TSFMs is computationally prohibitive and environmentally unsustainable for most regions. We present a training-free wrapper that corrects zero inflation for frozen TSFMs without updating any parameters. Our method restores discrete zero mass using empirical occurrence statistics, aligns positive-value distributions via probability-integral transforms, and applies Generalized Pareto tail mapping for extreme-value consistency. Experiments on South Australian rainfall show substantial gains with negligible overhead (<5,ms per forecast, compared to hundreds of GPU-hours for retraining). The proposed wrapper enables carbon-neutral, globally deployable climate services and directly advances the goals of UN SDG~13 (Climate Action).
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 531-541
Mitigating Latent Confounding Bias in Recommender Systems
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 531-541
Open AccessMitigating Latent Confounding Bias in Recommender Systems
- Open Access
- 17 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 105101-105112
RMixDA: A Random Compound Data Augmentation Operation Framework for Neural Machine Translation
In Neural Machine Translation (NMT), data augmentation is an effective method for improving model robustness by generating diverse augmented data from existing datasets. Typically, the quality of augmented data is evaluated based on its similarity and diversity to training data. Current approaches often rely on a single type of operation, limiting their ability to fully capture the range of possible variations in real-world data. This limitation will affect the robustness and generalization of model. To address this, we propose RMixDA: a Random Mixed Algorithm Framework For Data Augmentation, which dynamically integrates multiple NMT-oriented data augmentation methods. RMixDA defines an extensible collection of multi-augmentation operations using the Backus-Naur Form (BNF) framework, which categorizes data augmentation methods into pre-embedding (pre_embed_op), embedding (embed_op) and post-embedding (post_embed_op) levels. These operations are combined using a random walk algorithm to generate diverse augmented data, for maintaining both similarity and diversity. We further incorporate contrastive learning, identifying augmented data as positive or negative samples to evaluate similarity more effectively. Additionally, a novel evaluation method for augmented data quality is introduced, which is regularized by the NMT model’s loss function to improve the positive correlation between augmented data quality and model training. Extensive experimental studies demonstrate the effectiveness of RMixDA and its scalability for integrating diverse data augmentation operations.
- 17 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 105101-105112
Open AccessRMixDA: A Random Compound Data Augmentation Operation Framework for Neural Machine Translation
In Neural Machine Translation (NMT), data augmentation is an effective method for improving model robustness by generating diverse augmented data from existing datasets. Typically, the quality of augmented data is evaluated based on its similarity and diversity to training data. Current approaches often rely on a single type of operation, limiting their ability to fully capture the range of possible variations in real-world data. This limitation will affect the robustness and generalization of model. To address this, we propose RMixDA: a Random Mixed Algorithm Framework For Data Augmentation, which dynamically integrates multiple NMT-oriented data augmentation methods. RMixDA defines an extensible collection of multi-augmentation operations using the Backus-Naur Form (BNF) framework, which categorizes data augmentation methods into pre-embedding (pre_embed_op), embedding (embed_op) and post-embedding (post_embed_op) levels. These operations are combined using a random walk algorithm to generate diverse augmented data, for maintaining both similarity and diversity. We further incorporate contrastive learning, identifying augmented data as positive or negative samples to evaluate similarity more effectively. Additionally, a novel evaluation method for augmented data quality is introduced, which is regularized by the NMT model’s loss function to improve the positive correlation between augmented data quality and model training. Extensive experimental studies demonstrate the effectiveness of RMixDA and its scalability for integrating diverse data augmentation operations.