On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “self-augmentation”

Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learningcs.LG

Self-augmentation improves deep networks for few-shot learning with minimal training data.

problem Improving deep networks' generalization to unseen classes with limited training examples.

method Self-augmentation using self-mix and self-distillation techniques, combined with regional dropout and local representation learning.

result The method outperforms state-of-the-art few-shot learning methods on prevalent benchmarks.

few-shot learning deep networks generalization self-augmentation self-mix

2020-04-01abs ↗pdf ↗

SAIL: Self-Augmented Graph Contrastive Learningcs.LG

SAIL improves graph node representation learning by distilling knowledge between graphs.

problem Improving graph node representation learning with GNNs in unsupervised scenarios.

method SAIL framework with intra- and inter-graph knowledge distillation.

result SAIL consistently outperforms state-of-the-art baselines on various benchmark datasets.

Graph Neural Networks Node Representation Learning Self-Augmented Learning Graph Contrastive Learning Knowledge Distillation

2020-09-02abs ↗pdf ↗

Learning Discrete Representations via Information Maximizing Self-Augmented Trainingstat.ML

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks are promising to be used because they can model the non-linearity of data and s…

2017-02-28abs ↗pdf ↗

Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimationstat.ML

A new method improves text generation quality and diversity.

problem Exposure bias in Maximum Likelihood Estimation for text generation.

method ψ-MLE, a new training scheme based on density ratio estimation.

result ψ-MLE outperforms Maximum Likelihood Estimation and other models in text generation quality and diversity.

text generation maximum likelihood estimation density ratio estimation exposure bias auto-regressive models

2020-07-12abs ↗pdf ↗