Search Results for author:
Found 18 papers, 3 papers with code
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching
This finding shows that permutations found by WM mainly align the directions of singular vectors associated with large singular values across models.
Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation
We propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance with a limited number of training data.
Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
The proposed method embeds labeled and unlabeled data simultaneously in a task-specific space using a neural network, and the unlabeled data's labels are estimated by adapting classification or regression models in the embedding space.
Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers
Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two different domains.
Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space
With the proposed method, the OoD detection is performed by density estimation in a latent space.
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data.
Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions
Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem.
Transfer Learning with Pre-trained Conditional Generative Models
To transfer source knowledge without these assumptions, we propose a transfer learning method that uses deep generative models and is composed of the following two stages: pseudo pre-training (PP) and pseudo semi-supervised learning (P-SSL).
Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation
In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has recently been re-interpreted as a representative of the time scale of the state, i. e., a measure how long the RNN retains information on inputs.
Meta-Learning for Relative Density-Ratio Estimation
The closed-form solution enables fast and effective adaptation to a few instances, and its differentiability enables us to train our model such that the expected test error for relative DRE can be explicitly minimized after adapting to a few instances.
Few-shot Learning for Unsupervised Feature Selection
We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data.
Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
With a meta-learning framework, quick adaptation to each task and its effective backpropagation are important since the model is trained by the adaptation for each epoch.
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression
We theoretically and experimentally confirm that the weight loss landscape becomes sharper as the magnitude of the noise of adversarial training increases in the linear logistic regression model.
Meta-learning from Tasks with Heterogeneous Attribute Spaces
We propose a heterogeneous meta-learning method that trains a model on tasks with various attribute spaces, such that it can solve unseen tasks whose attribute spaces are different from the training tasks given a few labeled instances.
Few-shot Learning for Time-series Forecasting
Forecasting models are usually trained using time-series data in a specific target task.
Semi-supervised Anomaly Detection on Attributed Graphs
To learn node embeddings specialized for anomaly detection, in which there is a class imbalance due to the rarity of anomalies, the parameters of a GCN are trained to minimize the volume of a hypersphere that encloses the node embeddings of normal instances while embedding anomalous ones outside the hypersphere.
Transfer Anomaly Detection by Inferring Latent Domain Representations
The proposed method can infer the anomaly detectors for target domains without re-training by introducing the concept of latent domain vectors, which are latent representations of the domains and are used for inferring the anomaly detectors.
Zero-shot Domain Adaptation without Domain Semantic Descriptors
The proposed method can infer appropriate domain-specific models without any semantic descriptors by introducing the concept of latent domain vectors, which are latent representations for the domains and are used for inferring the models.
