Portrait de Sitao Luan n'est pas disponible

Sitao Luan

luansito@mila.quebec
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

Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
Sitao Luan
Harry Zhao
Mingde Zhao
Chenqing Hua
Xiao-Wen Chang
Doina Precup
The core operation of current Graph Neural Networks (GNNs) is the aggregation enabled by the graph Laplacian or message passing, which filte… (voir plus)rs the neighborhood node information. Though effective for various tasks, in this paper, we show that they are potentially a problematic factor underlying all GNN methods for learning on certain datasets, as they force the node representations similar, making the nodes gradually lose their identity and become indistinguishable. Hence, we augment the aggregation operations with their dual, i.e. diversification operators that make the node more distinct and preserve the identity. Such augmentation replaces the aggregation with a two-channel filtering process that, in theory, is beneficial for enriching the node representations. In practice, the proposed two-channel filters can be easily patched on existing GNN methods with diverse training strategies, including spectral and spatial (message passing) methods. In the experiments, we observe desired characteristics of the models and significant performance boost upon the baselines on 9 node classification tasks.
2022-11-21
NeurIPS.cc/2022/Workshop/GLFrontiers (accepté)
doi.org
openreview.net
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
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.
2021-12-06
Neural Information Processing Systems (Accept (Poster))
doi.org
openreview.net
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
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
2019-12-31
International Conference on Autonomous Agents and Multiagent Systems (publié)
doi.org
arxiv.org
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