2.9k citations
- The University of TokyoJP171 papers
- The Graduate University for Advanced Studies, SOKENDAIJP129 papers
- NTT Basic Research LaboratoriesJP96 papers
- Stanford UniversityUS80 papers
- Japan Science and Technology AgencyJP63 papers
- NTT (Japan)JP60 papers
- Centre National de la Recherche ScientifiqueFR55 papers
- New York UniversityUS49 papers
- New York University ShanghaiCN49 papers
- Hewlett-Packard (United Kingdom)GB41 papers
- East China Normal UniversityCN38 papers
- Japanese-French Laboratory for InformaticsJP38 papers
37 papers · 1 filter
Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?
Fumiaki Kimino, Ryoma Sato
Graph neural networks (GNNs) are widely used to represent complex interactions and relationships among entities. We investigate a multimodal model that combines two complementary i…
Efficient Neural Network Verification via Order Leading Exploration of Branch-and-Bound Trees
Guanqin Zhang, Kota Fukuda, Zhenya Zhang +4
The vulnerability of neural networks to adversarial perturbations has necessitated formal verification techniques that can rigorously certify the quality of neural networks. As the…
Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
Taisuke Kobayashi, Shingo Murata
This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, n…
Neuro-Symbolic Contrastive Learning for Cross-domain Inference
Mingyue Liu, Ryo Ueda, Zhen Wan +2
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on la…
Weber-Fechner Law in Temporal Difference learning derived from Control as Inference
Keiichiro Takahashi, Taisuke Kobayashi, Tomoya Yamanokuchi +1
This paper investigates a novel nonlinear update rule based on temporal difference (TD) errors in reinforcement learning (RL). The update rule in the standard RL states that the TD…
DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning
Taisuke Kobayashi
In reinforcement learning (RL), temporal difference (TD) error is known to be related to the firing rate of dopamine neurons. It has been observed that each dopamine neuron does no…