activity
20152021
most citedRobustness to Adversarial Perturbations in Learning from Incomplete Data

33 citations · 76 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG20215 cited

A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?

Hiroaki Mikami, Kenji Fukumizu, Shogo Murai +5

Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks. The most…

cs.LG20193 cited

MANGA: Method Agnostic Neural-policy Generalization and Adaptation

Homanga Bharadhwaj, Shoichiro Yamaguchi, Shin-ichi Maeda

In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework…

cs.LG2019

Reconnaissance and Planning algorithm for constrained MDP

Shin-ichi Maeda, Hayato Watahiki, Shintarou Okada +1

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while…

cs.LG2019

Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks

Kohei Hayashi, Taiki Yamaguchi, Yohei Sugawara +1

Tensor decomposition methods are widely used for model compression and fast inference in convolutional neural networks (CNNs). Although many decompositions are conceivable, only CP…

cs.LG201915 cited

Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis

Katsuhiko Ishiguro, Shin-ichi Maeda, Masanori Koyama

Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science. Current lines of GN…

cs.LG2018

BayesGrad: Explaining Predictions of Graph Convolutional Networks

Hirotaka Akita, Kosuke Nakago, Tomoki Komatsu +4

Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predict…