Portrait de Sitao Luan n'est pas disponible

Sitao Luan

Postdoctorat - McGill
Superviseur⋅e principal⋅e
Guillaume Rabusseau
Co-supervisor
Reihaneh Rabbany
Sujets de recherche
Apprentissage par renforcement
Exploration des données
IA pour la science
Raisonnement
Réseaux de neurones en graphes
Google Scholar
GitHub

Publications

Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
Sitao Luan
Chenqing Hua
Qincheng Lu
Jiaqi Zhu
Mingde Zhao
Shuyuan Zhang
Xiao-Wen Chang
Doina Precup
2021-09-11
ArXiv (prépublication)
arxiv.org
arxiv.org
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
Shuyuan Zhang
Mingde Zhao
Zhen Liu
Sitao Luan
Shuyuan Zhang
Doina Precup
Yoshua Bengio
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during plan… (voir plus)ning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.
2020-12-31
Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (publié)
doi.org
openreview.net
Revisit Policy Optimization in Matrix Form
Sitao Luan
Xiao-Wen Chang
Doina Precup
2019-09-18
ArXiv (prépublication)
arxiv.org
arxiv.org
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
Sitao Luan
Mingde Zhao
Xiao-Wen Chang
Doina Precup
Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. Howev… (voir plus)er, their bottlenecks still need to be addressed, and the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we theoretically analyze how existing Graph Convolutional Networks (GCNs) have limited expressive power due to the constraint of the activation functions and their architectures. We generalize spectral graph convolution and deep GCN in block Krylov subspace forms and devise two architectures, both with the potential to be scaled deeper but each making use of the multi-scale information in different ways. We further show that the equivalence of these two architectures can be established under certain conditions. On several node classification tasks, with or without the help of validation, the two new architectures achieve better performance compared to many state-of-the-art methods.
2018-12-31
NeurIPS (publié)
doi.org
arxiv.org
Meta-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
Mingde Zhao
Ian Porada
Sitao Luan
Xiao-Wen Chang
Doina Precup
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that lea… (voir plus)rn the value of a given policy, as well as algorithms which learn how to improve policies. TD-learning with eligibility traces provides a way to boost sample efficiency by temporal credit assignment, i.e. deciding which portion of a reward should be assigned to predecessor states that occurred at different previous times, controlled by a parameter
2018-12-31
arXiv (prépublication)
doi.org
arxiv.org