Advised by Bowen Du (杜博文), I received my bachelor’s degree from School of Computer Science and Engineering at Beihang University (北京航空航天大学计算机学院).

Under the guidance of my advisor Xi Xiao (肖喜) and co-advisor Shutao Xia (夏树涛), I received my master’s degree from the Department of Computer Science and Technology at Tsinghua University (清华大学计算机科学与技术系).

Currently, I am a third-year Ph.D. student in Tsinghua-Berkeley Shenzhen Institute, Tsinghua University (清华大学清华-伯克利深圳学院), fortunately, to be mentored by Xiao Li (肖皪) and co-advised by Max Shen (申作军).

My research interest includes reinforcement learning, recommeder systems, ad bidding, social network. I have published more than 10 papers at the top international AI conferences such as AAAI, ICRA, ICAPS, ICASSP, ICWS, ICME.

🔥 News

• 2022.12: 🧑‍🎨 I join Altered State Machine (ASM) remotely as a part-time AI research scientist.
• 2022.09: 🎉🎉 One paper is accepted by ICONIP 2022!

📚️ Portfolio of First-Author Papers

My full paper list is shown at my google scholar page .

📓 First-author papers

• Yao Y, Liu B, Zeng J, et al. i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Recommender Systems[J].arXiv preprint arXiv:2204.00281, 2022.
• Yao Y, Shen J, Xu J, et al. CLS: Cross Labeling Supervision for Semi-Supervised Learning[J]. arXiv preprint arXiv:2202.08502, 2022.
• Yao Y, Xiao L, An Z, et al. Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation[C]. (ICRA 2021)
• Yao Y, Xiao X, Zhang C, et al. Stability analysis of an SDILR model based on rumor recurrence on social media[J]. (Physica A, 2019)
• Yao Y, Xiao X, Zhang C, et al. Classifying Quality Centrality for Source Localization in Social Networks[C]. (ICWS 2018)

📔 Co-first-author papers (Names are in Alphabetical Order)

• Cao X, Yao Y, Li L, et al. iGrow: A Smart Agriculture Solution to Autonomous Greenhouse Control[C]. (AAAI 2022)
• An Z, Cao X, Yao Y, et al. A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy[C]. (ICAPS 2021)

📝 Publications Categorized by Research Area

🤖 Reinforcement Learning

• Zhang W, Xiao X, Yao Y, et al. MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning[J]. arXiv preprint arXiv:2108.01295, 2021.
• Cao X, Yao Y, Li L, et al. iGrow: A Smart Agriculture Solution to Autonomous Greenhouse Control[C]. Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(11): 11837-11845. (AAAI 2022)
• Zhang W, Cao X, Yao Y, et al. Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control[C]//Asian Conference on Machine Learning. PMLR, 2021: 1208-1223. (ACML 2021)
• Yao Y, Xiao L, An Z, et al. Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation[C]//2021 IEEE International Conference on Robotics and Automation. IEEE, 2021: 4202-4208. (ICRA 2021)
• An Z, Cao X, Yao Y, et al. A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy[C]//Proceedings of the International Conference on Automated Planning and Scheduling. 2021, 31: 436-444. (ICAPS 2021)
• Wang Z, Xiao X, Hu G, Yao Y, et al. Non-local Self-attention Structure for Function Approximation in Deep Reinforcement Learning[C]//ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2019: 3042-3046. (ICASSP 2019)

💸 Recommender System and AD Bidding

• Yao Y, Liu B, Zeng J, et al. i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Recommender Systems[J].arXiv preprint arXiv:2204.00281, 2022.

🎥 Computer Vision

• Yao Y, Shen J, Xu J, et al. CLS: Cross Labeling Supervision for Semi-Supervised Learning[J]. arXiv preprint arXiv:2202.08502, 2022.
• Zhang H, Lan Y, Dai T, Qiao R, Xu Y, Yao Y, Xia S. Residual Frame for Noisy Video Classification According to Perceptual Quality in Convolutional Neural Networks[C]//2019 IEEE International Conference on Multimedia and Expo. IEEE, 2019: 242-247. (ICME 2019)

🧑‍🤝‍🧑 Social Network

• Yao Y, Xiao X, Zhang C, et al. Stability analysis of an SDILR model based on rumor recurrence on social media[J]. Physica A: Statistical Mechanics and its Applications, 2019, 535: 122236. (Physica A, 2019)
• Yao Y, Xiao X, Zhang C, et al. Classifying Quality Centrality for Source Localization in Social Networks[C]//International Conference on Web Services. Springer, Cham, 2018: 295-307. (ICWS 2018)

🎖 Honors and Awards

• Rhino-bird Elite (TOP 5%), Tencent, 2022.
• Dean’s Scholarship, Tsinghua-Berkeley Shenzhen Institute (TBSI), 2019/2020/2021/2022.
• Friends of Tsinghua-Pinghu Talent Scholarship, 2021.

📖 Educations

• 2019.06 - 2022.12 (now), Phd, Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen.
• 2016.09 - 2019.06, Master, Department of Computer Science and Technology, Tsinghua Univeristy, Beijing.
• 2011.09 - 2015.06, Bachelor, School of Computer Science and Engineering, Beihang University, Beijing.

💬 Invited Talks

• To be updated.

💻 Internships

• 2022.02 - 2022.05, Inspir.AI, Reinforcement Learning Group, Shenzhen.
• 2021.05 - 2021.12, Tencent, Wechat, Data Quality Group, Shenzhen.
• 2020.12 - 2021.04, Bytedance Inc., Data, Vertical Strategy Group, Shenzhen.
• 2020.01 - 2020.11, Tencent, AI Lab, Machine Learning Group, Shenzhen.
• 2018.04 - 2018.07, Tencent, Wechat, Social Communication Group, Shenzhen.