1.3k citations · 1.5k across the 7 of their papers we have counts for
7 papers
Graph-Guided Network for Irregularly Sampled Multivariate Time Series
Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis +1
In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subse…
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
Xiang Zhang, Marinka Zitnik
Deep learning methods for graphs achieve remarkable performance across a variety of domains. However, recent findings indicate that small, unnoticeable perturbations of graph struc…
Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
Zheng Li, Ying Wei, Yu Zhang +3
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or…
Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation
Xiang Zhang, Yann LeCun
This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE consists of an auto-encoder where the interna…
Byte-Level Recursive Convolutional Auto-Encoder for Text
Xiang Zhang, Yann LeCun
This article proposes to auto-encode text at byte-level using convolutional networks with a recursive architecture. The motivation is to explore whether it is possible to have scal…
Universum Prescription: Regularization using Unlabeled Data
Xiang Zhang, Yann LeCun
This paper shows that simply prescribing "none of the above" labels to unlabeled data has a beneficial regularization effect to supervised learning. We call it universum prescripti…
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Pierre Sermanet, David Eigen, Xiang Zhang +3
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be effi…