Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Lu, Songtao"'
Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification} that sample
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e27f5933c8becef690aa0092ee487024
The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adversarial attacks, which creates a stringent need to build robust GNN a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5bdcba92f607a09aa7af64b3d4f1314
http://arxiv.org/abs/2210.01002
http://arxiv.org/abs/2210.01002
Autor:
Lu, Songtao
Nonconvex constrained optimization problems can be used to model a number of machine learning problems, such as multi-class Neyman-Pearson classification and constrained Markov decision processes. However, such kinds of problems are challenging becau
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cd8cce3675b24058d4a8ff3dcb6e51e
http://arxiv.org/abs/2207.05650
http://arxiv.org/abs/2207.05650
Deep neural networks have been shown as a class of useful tools for addressing signal recognition issues in recent years, especially for identifying the nonlinear feature structures of signals. However, this power of most deep learning techniques hea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae68337a4639394050d93e6554a340cf
Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancing representation learning. Natural views are often handled by multivie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36d6556e343fd74fcc6581fdbcf29bf4
Autor:
Zhao, Pu, Ram, Parikshit, Lu, Songtao, Yao, Yuguang, Bouneffouf, Djallel, Lin, Xue, Liu, Sijia
Adversarial perturbations are critical for certifying the robustness of deep learning models. A ``universal adversarial perturbation'' (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an image-wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4806baafce9dedb16d42c3072f368778
http://arxiv.org/abs/2009.13714
http://arxiv.org/abs/2009.13714