Aijun Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Aijun Bai has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Xiaoping Chen
University of Science and Technology of China
4 shared publications- Feng Wu
University of Science and Technology of China
3 shared publications - Bing-Rong Lin
Google LLC, Mountain View, CA, USA
2 shared publications - Marc Najork
Google DeepMind, Mountain View, California, USA
2 shared publications - Michael Bendersky
Google, Mountain View, CA, USA
2 shared publications - Pratyush Kar
Google LLC, Paris, France
2 shared publications
Latest Publications
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4502-4508
Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score-sensitive applications. Though a simple multi-objective approach that combines a regression and a ranking objective can effectively learn scale-calibrated scores, we argue that the two objectives are not necessarily compatible, which makes the trade-off less ideal for either of them. In this paper, we propose a practical regression compatible ranking (RCR) approach that achieves a better trade-off, where the two ranking and regression components are proved to be mutually aligned. Although the same idea applies to ranking with both binary and graded relevance, we mainly focus on binary labels in this paper. We evaluate the proposed approach on several public LTR benchmarks and show that it consistently achieves either best or competitive result in terms of both regression and ranking metrics, and significantly improves the Pareto frontiers in the context of multi-objective optimization. Furthermore, we evaluated the proposed approach on YouTube Search and found that it not only improved the ranking quality of the production pCTR model, but also brought gains to the click prediction accuracy. The proposed approach has been successfully deployed in the YouTube production system.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4502-4508
Open AccessRegression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score-sensitive applications. Though a simple multi-objective approach that combines a regression and a ranking objective can effectively learn scale-calibrated scores, we argue that the two objectives are not necessarily compatible, which makes the trade-off less ideal for either of them. In this paper, we propose a practical regression compatible ranking (RCR) approach that achieves a better trade-off, where the two ranking and regression components are proved to be mutually aligned. Although the same idea applies to ranking with both binary and graded relevance, we mainly focus on binary labels in this paper. We evaluate the proposed approach on several public LTR benchmarks and show that it consistently achieves either best or competitive result in terms of both regression and ranking metrics, and significantly improves the Pareto frontiers in the context of multi-objective optimization. Furthermore, we evaluated the proposed approach on YouTube Search and found that it not only improved the ranking quality of the production pCTR model, but also brought gains to the click prediction accuracy. The proposed approach has been successfully deployed in the YouTube production system.
- Open Access
Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score-sensitive applications. Though a simple multi-objective approach that combines a regression and a ranking objective can effectively learn scale-calibrated scores, we argue that the two objectives are not necessarily compatible, which makes the trade-off less ideal for either of them. In this paper, we propose a practical regression compatible ranking (RCR) approach that achieves a better trade-off, where the two ranking and regression components are proved to be mutually aligned. Although the same idea applies to ranking with both binary and graded relevance, we mainly focus on binary labels in this paper. We evaluate the proposed approach on several public LTR benchmarks and show that it consistently achieves either best or competitive result in terms of both regression and ranking metrics, and significantly improves the Pareto frontiers in the context of multi-objective optimization. Furthermore, we evaluated the proposed approach on YouTube Search and found that it not only improved the ranking quality of the production pCTR model, but also brought gains to the click prediction accuracy. The proposed approach has been successfully deployed in the YouTube production system.
Open AccessRegression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score-sensitive applications. Though a simple multi-objective approach that combines a regression and a ranking objective can effectively learn scale-calibrated scores, we argue that the two objectives are not necessarily compatible, which makes the trade-off less ideal for either of them. In this paper, we propose a practical regression compatible ranking (RCR) approach that achieves a better trade-off, where the two ranking and regression components are proved to be mutually aligned. Although the same idea applies to ranking with both binary and graded relevance, we mainly focus on binary labels in this paper. We evaluate the proposed approach on several public LTR benchmarks and show that it consistently achieves either best or competitive result in terms of both regression and ranking metrics, and significantly improves the Pareto frontiers in the context of multi-objective optimization. Furthermore, we evaluated the proposed approach on YouTube Search and found that it not only improved the ranking quality of the production pCTR model, but also brought gains to the click prediction accuracy. The proposed approach has been successfully deployed in the YouTube production system.
- 7 September 2018
- Published by Springer Nature
- p. 190-203
Concurrent Hierarchical Reinforcement Learning for RoboCup Keepaway
- 7 September 2018
- Published by Springer Nature
- p. 190-203
Concurrent Hierarchical Reinforcement Learning for RoboCup Keepaway
- 15 August 2018
- Published by Springer Nature in Applied Intelligence
- Vol. 48 (12) , 4998-5018
Posterior sampling for Monte Carlo planning under uncertainty
- 15 August 2018
- Published by Springer Nature in Applied Intelligence
- Vol. 48 (12) , 4998-5018
Posterior sampling for Monte Carlo planning under uncertainty
- Open Access
- 15 July 2015
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 6 (4) , 1-28
Online Planning for Large Markov Decision Processes with Hierarchical Decomposition
Markov decision processes (MDPs) provide a rich framework for planning under uncertainty. However, exactly solving a large MDP is usually intractable due to the “curse of dimensionality”— the state space grows exponentially with the number of state variables. Online algorithms tackle this problem by avoiding computing a policy for the entire state space. On the other hand, since online algorithm has to find a near-optimal action online in almost real time, the computation time is often very limited. In the context of reinforcement learning, MAXQ is a value function decomposition method that exploits the underlying structure of the original MDP and decomposes it into a combination of smaller subproblems arranged over a task hierarchy. In this article, we present MAXQ-OP—a novel online planning algorithm for large MDPs that utilizes MAXQ hierarchical decomposition in online settings. Compared to traditional online planning algorithms, MAXQ-OP is able to reach much more deeper states in the search tree with relatively less computation time by exploiting MAXQ hierarchical decomposition online. We empirically evaluate our algorithm in the standard Taxi domain—a common benchmark for MDPs—to show the effectiveness of our approach. We have also conducted a long-term case study in a highly complex simulated soccer domain and developed a team named WrightEagle that has won five world champions and five runners-up in the recent 10 years of RoboCup Soccer Simulation 2D annual competitions. The results in the RoboCup domain confirm the scalability of MAXQ-OP to very large domains.
- 15 July 2015
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 6 (4) , 1-28
Open AccessOnline Planning for Large Markov Decision Processes with Hierarchical Decomposition
Markov decision processes (MDPs) provide a rich framework for planning under uncertainty. However, exactly solving a large MDP is usually intractable due to the “curse of dimensionality”— the state space grows exponentially with the number of state variables. Online algorithms tackle this problem by avoiding computing a policy for the entire state space. On the other hand, since online algorithm has to find a near-optimal action online in almost real time, the computation time is often very limited. In the context of reinforcement learning, MAXQ is a value function decomposition method that exploits the underlying structure of the original MDP and decomposes it into a combination of smaller subproblems arranged over a task hierarchy. In this article, we present MAXQ-OP—a novel online planning algorithm for large MDPs that utilizes MAXQ hierarchical decomposition in online settings. Compared to traditional online planning algorithms, MAXQ-OP is able to reach much more deeper states in the search tree with relatively less computation time by exploiting MAXQ hierarchical decomposition online. We empirically evaluate our algorithm in the standard Taxi domain—a common benchmark for MDPs—to show the effectiveness of our approach. We have also conducted a long-term case study in a highly complex simulated soccer domain and developed a team named WrightEagle that has won five world champions and five runners-up in the recent 10 years of RoboCup Soccer Simulation 2D annual competitions. The results in the RoboCup domain confirm the scalability of MAXQ-OP to very large domains.
- 1 January 2013
- Published by Springer Nature
- p. 141-153
Towards a Principled Solution to Simulated Robot Soccer
- 1 January 2013
- Published by Springer Nature
- p. 141-153
Towards a Principled Solution to Simulated Robot Soccer
- 1 January 2012
- Published by Springer Nature
- p. 1-12
WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions
- 1 January 2012
- Published by Springer Nature
- p. 1-12
WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions