1.3k citations
- Mitsubishi Electric Research Laboratories (United States)US14 papers
- Mitsubishi Electric (United States)US14 papers
- The University of TokyoJP13 papers
- The University of OsakaJP9 papers
- Tokai UniversityJP9 papers
- Chalmers University of TechnologySE7 papers
- Nagoya UniversityJP6 papers
- University of ToyamaJP6 papers
- National Astronomical Observatory of JapanJP5 papers
- NTT (Japan)JP5 papers
- Centre for Quantum TechnologiesSG4 papers
- Kyoto UniversityJP4 papers
11 papers · 1 filter
Sampling and Recovery of Graph Signals based on Graph Neural Networks
Siheng Chen, Maosen Li, Ya Zhang
We propose interpretable graph neural networks for sampling and recovery of graph signals, respectively. To take informative measurements, we propose a new graph neural sampling mo…
Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation
Kei Ota, Devesh K. Jha, Diego Romeres +7
Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success…
Graph Cross Networks with Vertex Infomax Pooling
Maosen Li, Siheng Chen, Ya Zhang +1
We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph,…
On The Convergence of Euler Discretization of Finite-Time Convergent Gradient Flows
Siqi Zhang, Mouhacine Benosman, Orlando Romero
In this study, we investigate the performance of two novel first-order optimization algorithms, namely the rescaled-gradient flow (RGF) and the signed-gradient flow (SGF). These al…
Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction
Toshiaki Koike-Akino, Ye Wang
We propose a new concept of rateless auto-encoders (RL-AEs) that enable a flexible latent dimensionality, which can be seamlessly adjusted for varying distortion and dimensionality…
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
Kei Ota, Tomoaki Oiki, Devesh K. Jha +2
Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training lar…