TY  - JOUR
AU  - Diego Velazquez
AU  - Pau Rodriguez
AU  - Josep M. Gonfaus
AU  - Xavier Roca
AU  - Jordi Gonzalez
PY  - 2022//
TI  - A Closer Look at Embedding Propagation for Manifold Smoothing
T2  - JMLR
JO  - Journal of Machine Learning Research
SP  - 1
EP  - 27
VL  - 23
IS  - 252
KW  - Regularization
KW  - emi-supervised learning
KW  - self-supervised learning
KW  - adversarial robustness
KW  - few-shot classification
N2  - Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be sensitive to out-of-distribution (OOD) data.Self- and semi-supervised training schemes reduce the amount of annotated data required during the training process. However, OOD generalization remains a major challenge for most methods. Strategies that promote smoother decision boundaries play an important role in out-of-distribution generalization. For example, embedding propagation (EP) for manifold smoothing has recently shown to considerably improve the OOD performance for few-shot classification. EP achieves smoother class manifolds by building a graph from sample embeddings and propagating information through the nodes in an unsupervised manner. In this work, we extend the original EP paper providing additional evidence and experiments showing that it attains smoother class embedding manifolds and improves results in settings beyond few-shot classification. Concretely, we show that EP improves the robustness of neural networks against multiple adversarial attacks as well as semi- andself-supervised learning performance.
UR  - http://jmlr.org/papers/v23/21-0468.html
N1  - exported from refbase (http://refbase.cvc.uab.es/show.php?record=3762), last updated on Tue, 25 Apr 2023 10:33:45 +0200
ID  - Diego Velazquez2022
ER  -