Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach
- Giorgio Patrini, A. Rozza, A. Menon, R. Nock, Lizhen Qu
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 13 September 2016
It is proved that, when ReLU is the only non-linearity, the loss curvature is immune to class-dependent label noise, and it is shown how one can estimate these probabilities, adapting a recent technique for noise estimation to the multi-class setting, and providing an end-to-end framework.
STransE: a novel embedding model of entities and relationships in knowledge bases
STransE is a simple combination of the SE and TransE models, but it obtains better link prediction performance on two benchmark datasets than previous embedding models, and can serve as a new baseline for the more complex models in the link prediction task.
Timely YAGO: harvesting, querying, and visualizing temporal knowledge from Wikipedia
This paper introduces Timely YAGO, which extends the previously built knowledge base Y AGO with temporal aspects, and extracts temporal facts from Wikipedia infoboxes, categories, and lists in articles, and integrates these into the TimelyYAGO knowledge base.
Making Neural Networks Robust to Label Noise: a Loss Correction Approach
It is proved that, when ReLU is the only non-linearity, the loss curvature is immune to class-dependent label noise, and the proposed procedures for loss correction simply amount to at most a matrix inversion and multiplication.
Automatic Generation of Grounded Visual Questions
- Shijie Zhang, Lizhen Qu, Shaodi You, Zhenglu Yang, Jiawan Zhang
- Computer ScienceIJCAI
- 20 December 2016
This paper proposes the first model to be able to generate visually grounded questions with diverse types for a single image and shows that the model outperforms the strongest baseline in terms of both correctness and diversity with a wide margin.
Privacy-Aware Text Rewriting
It is argued that a better way to protect data providers is to remove the trails of sensitive information before publishing the data, and proposes a new privacy-aware text rewriting task and explores two privacy- aware back-translation methods for the task, based on adversarial training and approximate fairness risk.
The Bag-of-Opinions Method for Review Rating Prediction from Sparse Text Patterns
Experiments show that the bag- of-opinions method outperforms prior state-of-the-art techniques for review rating prediction, and is presented as a constrained ridge regression algorithm for learning opinion scores.
Neighborhood Mixture Model for Knowledge Base Completion
Experimental results show that the neighborhood information significantly helps to improve the results of the TransE model, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.
Harvesting facts from textual web sources by constrained label propagation
A system called PRAVDA is proposed based on a new kind of label propagation algorithm with a judiciously designed loss function, which iteratively processes the graph to label good temporal facts for a given set of target relations.
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
This paper attempts to alleviate this severe binary vulnerability detection bottleneck by leveraging recent advances in deep learning representations and proposes the Maximal Divergence Sequential Auto-Encoder, which outperform the baselines in all performance measures of interest.