The University of Queensland

Improving Traffic Load Prediction with Multi-modality : A Case Study of Brisbane

Tran, Khai Phan, Chen, Weitong and Xu, Miao (2022). Improving Traffic Load Prediction with Multi-modality : A Case Study of Brisbane. Lecture Notes in Computer Science. (pp. 254-266) Cham: Springer International Publishing. doi: 10.1007/978-3-030-97546-3_21

Personalized on-device e-health analytics with decentralized block coordinate descent

Ye, Guanhua, Yin, Hongzhi, Chen, Tong, Xu, Miao, Nguyen, Quoc Viet Hung and Song, Jiangning (2022). Personalized on-device e-health analytics with decentralized block coordinate descent. IEEE Journal of Biomedical and Health Informatics, 26 (6), 1-1. doi: 10.1109/JBHI.2022.3140455

Learning from group supervision: the impact of supervision deficiency on multi-label learning

Xu, Miao and Guo, Lan-Zhe (2021). Learning from group supervision: the impact of supervision deficiency on multi-label learning. Science China Information Sciences, 64 (3) 130101. doi: 10.1007/s11432-020-3132-4

Robust multi-label learning with PRO Loss

Xu, Miao, Li, Yu-Feng and Zhou, Zhi-Hua (2020). Robust multi-label learning with PRO Loss. IEEE Transactions on Knowledge and Data Engineering, 32 (8) 8680669, 1610-1624. doi: 10.1109/tkde.2019.2908898

Kernel method for matrix completion with side information and its application in multi-label learning

Xu, Miao and Zhou, Zhi-Hua (2017). Kernel method for matrix completion with side information and its application in multi-label learning. Scientia Sinica Informationis, 48 (1), 47-59. doi: 10.1360/n112016-00279

Towards better generalization for neural network-based SAT solvers

Zhang, Chenhao, Zhang, Yanjun, Mao, Jeff, Chen, Weitong, Yue, Lin, Bai, Guangdong and Xu, Miao (2022). Towards better generalization for neural network-based SAT solvers. 26th Pacific-Asia Conference, PAKDD 2022, Chengdu, China, 16-19 May 2022. Springer Science and Business Media Deutschland GmbH. doi: 10.1007/978-3-031-05936-0_16

Investigating active positive-unlabeled learning with deep networks

Han, Kun, Chen, Weitong and Xu, Miao (2022). Investigating active positive-unlabeled learning with deep networks. Australasian Joint Conference on Artificial Intelligence (AI), Electr Network, 2-4 February 2022. Cham, Switzerland: Springer Nature Switzerland. doi: 10.1007/978-3-030-97546-3_49

STCT: Spatial-temporal conv-transformer network for cardiac arrhythmias recognition

Qiu, Yixuan, Chen, Weitong, Yue, Lin, Xu, Miao and Zhu, Baofeng (2022). STCT: Spatial-temporal conv-transformer network for cardiac arrhythmias recognition. International Conference on Advanced Data Mining and Applications, Sydney, NSW, Australia, 2-4 February 2022. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-95405-5_7

Multi-hop reading on memory neural network with selective coverage for medication recommendation

Wang, Yanda, Chen, Weitong, Pi, Dechang, Yue, Lin, Xu, Miao and Li, Xue (2021). Multi-hop reading on memory neural network with selective coverage for medication recommendation. ACM International Conference on Information & Knowledge Management, Virtual Event, 1-5 November 2021. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3459637.3482278

Positive-unlabeled learning from imbalanced data

Su, Guangxin, Chen, Weitong and Xu, Miao (2021). Positive-unlabeled learning from imbalanced data. Thirtieth International Joint Conference on Artificial Intelligence, Montreal, Canada, 19-27 August 2021. California, United States: International Joint Conferences on Artificial Intelligence Organization. doi: 10.24963/ijcai.2021/412

Self-supervised adversarial distribution regularization for medication recommendation

Wang, Yanda, Chen, Weitong, PI, Dechang, Yue, Lin, Wang, Sen and Xu, Miao (2021). Self-supervised adversarial distribution regularization for medication recommendation. Thirtieth International Joint Conference on Artificial Intelligence, Montreal, Canada, 19-27 August 2021. California, United States: International Joint Conferences on Artificial Intelligence Organization. doi: 10.24963/ijcai.2021/431

Pointwise binary classification with pairwise confidence comparisons

Feng, Lei, Shu, Senlin, Lu, Nan, Han, Bo, Xu, Miao, Niu, Gang, An, Bo and Sugiyama, Masashi (2021). Pointwise binary classification with pairwise confidence comparisons. International Conference on Machine Learning (ICML), Virtual, 18-24 July, 2021. San Diego, CA, United States: JMLR.

SIGUA: Forgetting may make learning with noisy labels more robust

Han, Bo, Niu, Gang, Yu, Xingrui, Yao, Quanming, Xu, Miao, Tsang, Ivor W. and Sugiyama, Masashi (2020). SIGUA: Forgetting may make learning with noisy labels more robust. International Conference on Machine Learning (ICML), Virtual, 13-18 July, 2020. San Diego, CA, United States: JMLR.

Progressive identification of true labels for partial-label learning

Lvy, Jiaqi, Xu, Miao, Feng, Lei, Niu, Gang, Geng, Xin and Sugiyama, Masashi (2020). Progressive identification of true labels for partial-label learning. 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, 12-18 July 2020. International Machine Learning Society.

Provably consistent partial-label learning

Feng, Lei, Lv, Jiaqi, Han, Bo, Xu, Miao, Niu, Gang, Geng, Xin, An, Bo and Sugiyama, Masashi (2020). Provably consistent partial-label learning. Conference on Neural Information Processing Systems, Vancouver, Canada, 6-12 December 2020. Maryland Heights, MO, United States: Morgan Kaufmann Publishers.

Trading personalization for accuracy: data debugging in collaborative filtering

Chen, Long, Yao, Yuan, Xu, Feng, Xu, Miao and Tong, Hanghang (2020). Trading personalization for accuracy: data debugging in collaborative filtering. Conference on Neural Information Processing Systems, Vancouver, Canada, 6-12 December 2020. Maryland Heights, MO, United States: Morgan Kaufmann Publishers.

Clipped Matrix Completion: A Remedy for Ceiling Effects

Teshima, Takeshi, Xu, Miao, Sato, Issei and Sugiyama, Masashi (2019). Clipped Matrix Completion: A Remedy for Ceiling Effects. Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI United States, 27 January – 1 February 2019. Association for the Advancement of Artificial Intelligence (AAAI). doi: 10.1609/aaai.v33i01.33015151

Co-teaching: Robust training of deep neural networks with extremely noisy labels

Han, Bo, Yao, Quanming, Yu, Xingrui, Niu, Gang, Xu, Miao, Hu, Weihua, Tsang, Ivor W. and Sugiyama, Masashi (2018). Co-teaching: Robust training of deep neural networks with extremely noisy labels. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, Canada, 2-8 December, 2018. Maryland Heights, MO, United States: Morgan Kaufmann Publishers. doi: 10.5555/3327757.3327944

Active Feature Acquisition with Supervised Matrix Completion

Huang, Sheng-Jun, Xu, Miao, Xie, Ming-Kun, Sugiyama, Masashi, Niu, Gang and Chen, Songcan (2018). Active Feature Acquisition with Supervised Matrix Completion. 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, United Kingdom, July 2018. New York, NY United States: ACM. doi: 10.1145/3219819.3220084

Incomplete Label Distribution Learning

Xu, Miao and Zhou, Zhi-Hua (2017). Incomplete Label Distribution Learning. Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, VIC Australia, 19-25 August 2017. Melbourne, VIC Australia: International Joint Conferences on Artificial Intelligence Organization. doi: 10.24963/ijcai.2017/443

CUR algorithm for partially observed matrices

Xu, Miao, Jin, Rong and Zhou, Zhi-Hua (2015). CUR algorithm for partially observed matrices. 32nd International Conference on Machine Learning, Lille, France, 7-9 July, 2015. San Diego, CA, United States: JMLR.

Multi-label learning with PRO LOSS

Xu, Miao, Li, Yu-Feng and Zhou, Zhi-Hua (2013). Multi-label learning with PRO LOSS. AAAI-13: Twenty-Seventh Conference on Artificial Intelligence, Bellevue, WA USA, 14-18 July 2013.

Speedup matrix completion with side information: application to multi-label learning

Xu, Miao, Jin, Rong and Zhou, Zhi-Hua (2013). Speedup matrix completion with side information: application to multi-label learning. NIPS'13: Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, NV USA, 5-10 December 2013. Maryland Heights, MO USA: Morgan Kaufmann Publishers.