Search Results for author: Wee Sun Lee

Found 45 papers, 18 papers with code

None Class Ranking Loss for Document-Level Relation Extraction

1 code implementation1 May 2022 Yang Zhou, Wee Sun Lee

This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions.

Emotion Classification Multi-Label Classification +1

Graph Representation Learning with Individualization and Refinement

no code implementations17 Mar 2022 Mohammed Haroon Dupty, Wee Sun Lee

Individualization refers to artificially distinguishing a node in the graph and refinement is the propagation of this information to other nodes through message passing.

Graph Representation Learning

Combining Reinforcement Learning and Optimal Transport for the Traveling Salesman Problem

no code implementations2 Mar 2022 Yong Liang Goh, Wee Sun Lee, Xavier Bresson, Thomas Laurent, Nicholas Lim

This paper exemplifies the integration of entropic regularized optimal transport techniques as a layer in a deep reinforcement learning network.

Combinatorial Optimization reinforcement-learning +1

Context-Hierarchy Inverse Reinforcement Learning

no code implementations25 Feb 2022 Wei Gao, David Hsu, Wee Sun Lee

To solve these issues, we present Context Hierarchy IRL(CHIRL), a new IRL algorithm that exploits the context to scale up IRL and learn reward functions of complex behaviors.

Autonomous Driving reinforcement-learning

ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search

no code implementations3 Feb 2022 Dixant Mittal, Siddharth Aravindan, Wee Sun Lee

A tree-based online search algorithm iteratively simulates trajectories and updates Q-value information on a set of states represented by a tree structure.

EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning

no code implementations29 Sep 2021 Siddharth Aravindan, Dixant Mittal, Wee Sun Lee

These layers rely on Gaussian dropouts and are inserted in between the layers of the deep neural network model to help facilitate variational Thompson sampling.

Atari Games Model-based Reinforcement Learning +1

PF-GNN: Differentiable particle filtering based approximation of universal graph representations

1 code implementation ICLR 2022 Mohammed Haroon Dupty, Yanfei Dong, Wee Sun Lee

Message passing Graph Neural Networks (GNNs) are known to be limited in expressive power by the 1-WL color-refinement test for graph isomorphism.

Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning

1 code implementation5 Jul 2021 Muhammad Rizki Maulana, Wee Sun Lee

Ensemble and auxiliary tasks are both well known to improve the performance of machine learning models when data is limited.

Atari Games Q-Learning +1

Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects

no code implementations25 Apr 2021 Xiao Ma, David Hsu, Wee Sun Lee

Manipulating deformable objects, such as ropes and clothing, is a long-standing challenge in robotics, because of their large degrees of freedom, complex non-linear dynamics, and self-occlusion in visual perception.

Contrastive Learning Deformable Object Manipulation +1

State-Aware Variational Thompson Sampling for Deep Q-Networks

no code implementations7 Feb 2021 Siddharth Aravindan, Wee Sun Lee

We derive a variational Thompson sampling approximation for DQNs which uses a deep network whose parameters are perturbed by a learned variational noise distribution.

Factor Graph Molecule Network for Structure Elucidation

no code implementations10 Dec 2020 Hieu Le Trung, Yiqing Xu, Wee Sun Lee

Designing a network to learn a molecule structure given its physical/chemical properties is a hard problem, but is useful for drug discovery tasks.

Drug Discovery Relational Reasoning

Factor Graph Neural Networks

no code implementations NeurIPS 2020 Zhen Zhang, Fan Wu, Wee Sun Lee

Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks.

Neuralizing Efficient Higher-order Belief Propagation

no code implementations19 Oct 2020 Mohammed Haroon Dupty, Wee Sun Lee

In this paper, we propose to combine these approaches to learn better node and graph representations.

Inductive Bias

Contrastive Variational Reinforcement Learning for Complex Observations

1 code implementation6 Aug 2020 Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee

This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL.

Atari Games Continuous Control +3

Understanding and Resolving Performance Degradation in Graph Convolutional Networks

1 code implementation12 Jun 2020 Kuangqi Zhou, Yanfei Dong, Kaixin Wang, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng

In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.

Multiplicative Gaussian Particle Filter

no code implementations29 Feb 2020 Xuan Su, Wee Sun Lee, Zhen Zhang

We propose a new sampling-based approach for approximate inference in filtering problems.

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations

1 code implementation ICLR 2020 Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee, Nan Ye

The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making.

Atari Games Decision Making +2

Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition

no code implementations22 Nov 2019 Mohammed Haroon Dupty, Zhen Zhang, Wee Sun Lee

We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the form of triplets of (subject, predicate, object).

Tensor Decomposition Visual Relationship Detection

Factor Graph Neural Network

1 code implementation3 Jun 2019 Zhen Zhang, Fan Wu, Wee Sun Lee

Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks.

Particle Filter Recurrent Neural Networks

1 code implementation30 May 2019 Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee

Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data.

General Classification Stock Price Prediction +1

LeTS-Drive: Driving in a Crowd by Learning from Tree Search

no code implementations29 May 2019 Panpan Cai, Yuanfu Luo, Aseem Saxena, David Hsu, Wee Sun Lee

LeTS-Drive leverages the robustness of planning and the runtime efficiency of learning to enhance the performance of both.

Autonomous Driving Imitation Learning

Differentiable Algorithm Networks for Composable Robot Learning

no code implementations28 May 2019 Peter Karkus, Xiao Ma, David Hsu, Leslie Pack Kaelbling, Wee Sun Lee, Tomas Lozano-Perez

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems.

Navigate

Factored Contextual Policy Search with Bayesian Optimization

no code implementations26 Apr 2019 Robert Pinsler, Peter Karkus, Andras Kupcsik, David Hsu, Wee Sun Lee

Our key observation is that experience can be directly generalized over target contexts.

Active Learning

Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification

1 code implementation EMNLP 2018 Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain.

Classification General Classification +1

Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation

no code implementations17 Jul 2018 Peter Karkus, David Hsu, Wee Sun Lee

We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i. e. a deep neural network.

Navigate Robot Navigation

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

1 code implementation Robotics: Science and Systems 2018 Jue Kun Li, David Hsu, Wee Sun Lee

This paper introduces Push-Net, a deep recurrent neural network model, which enables a robot to push objects of unknown physical properties for re-positioning and re-orientation, using only visual camera images as input.

PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrians

no code implementations30 May 2018 Yuanfu Luo, Panpan Cai, Aniket Bera, David Hsu, Wee Sun Lee, Dinesh Manocha

Our planning system combines a POMDP algorithm with the pedestrian motion model and runs in near real time.

Robotics

Particle Filter Networks with Application to Visual Localization

2 code implementations23 May 2018 Peter Karkus, David Hsu, Wee Sun Lee

Particle filtering is a powerful approach to sequential state estimation and finds application in many domains, including robot localization, object tracking, etc.

Object Tracking Visual Localization

HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertainty

1 code implementation17 Feb 2018 Panpan Cai, Yuanfu Luo, David Hsu, Wee Sun Lee

Planning under uncertainty is critical for robust robot performance in uncertain, dynamic environments, but it incurs high computational cost.

Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation

2 code implementations16 Oct 2017 Wei Gao, David Hsu, Wee Sun Lee, ShengMei Shen, Karthikk Subramanian

How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information?

Autonomous Navigation Navigate

Tensor Belief Propagation

no code implementations ICML 2017 Andrew Wrigley, Wee Sun Lee, Nan Ye

We propose a new approximate inference algorithm for graphical models, tensor belief propagation, based on approximating the messages passed in the junction tree algorithm.

An Unsupervised Neural Attention Model for Aspect Extraction

3 code implementations ACL 2017 Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

Unlike topic models which typically assume independently generated words, word embedding models encourage words that appear in similar contexts to be located close to each other in the embedding space.

Aspect Extraction Domain Adaptation +2

QMDP-Net: Deep Learning for Planning under Partial Observability

3 code implementations NeurIPS 2017 Peter Karkus, David Hsu, Wee Sun Lee

It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture.

Factored Contextual Policy Search with Bayesian Optimization

no code implementations6 Dec 2016 Peter Karkus, Andras Kupcsik, David Hsu, Wee Sun Lee

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts".

Active Learning

DESPOT: Online POMDP Planning with Regularization

no code implementations NeurIPS 2013 Nan Ye, Adhiraj Somani, David Hsu, Wee Sun Lee

We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy.

Autonomous Driving

POMDP-lite for Robust Robot Planning under Uncertainty

no code implementations16 Feb 2016 Min Chen, Emilio Frazzoli, David Hsu, Wee Sun Lee

We show that a POMDP-lite is equivalent to a set of fully observable Markov decision processes indexed by a hidden parameter and is useful for modeling a variety of interesting robotic tasks.

reinforcement-learning

Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space

no code implementations NeurIPS 2013 Xinhua Zhang, Wee Sun Lee, Yee Whye Teh

For the representer theorem to hold, the linear functionals are required to be bounded in the RKHS, and we show that this is true for a variety of commonly used RKHS and invariances.

Monte Carlo Bayesian Reinforcement Learning

no code implementations27 Jun 2012 Yi Wang, Kok Sung Won, David Hsu, Wee Sun Lee

Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them.

reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.