Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
Differentiable Learning of Logical Rules for Knowledge Base Reasoning
TLDR
A framework, Neural Logic Programming, is proposed that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model and outperforms prior work on multiple knowledge base benchmark datasets, including Freebase and WikiMovies.
View Paper
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
TLDR
This paper develops a novel post-hoc visual explanation method called Score-CAM based on class activation mapping that outperforms previous methods on both recognition and localization tasks, it also passes the sanity check.
View on IEEE
Good Semi-supervised Learning That Requires a Bad GAN
TLDR
Theoretically, it is shown that given the discriminator objective, good semisupervised learning indeed requires a bad generator, and a novel formulation based on the analysis that substantially improves over feature matching GANs is derived, obtaining state-of-the-art results on multiple benchmark datasets.
View PDF on arXiv
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
TLDR
The proposed Class-Rebalancing Self-Training (CReST), a simple yet effective framework to improve existing semi-supervised learning methods on class-imbalanced data, and a progressive distribution alignment to adaptively adjust the rebalancing strength dubbed CReST+.
View on IEEE
Selective inference for group-sparse linear models
TLDR
The main technical result gives the precise distribution of the magnitude of the projection of the data onto a given subspace, and enables the development of inference procedures for a broad class of group-sparse selection methods, including the group lasso, iterative hard thresholding, and forward stepwise regression.
View PDF on arXiv
Label Transfer from APOGEE to LAMOST: Precise Stellar Parameters for 450,000 LAMOST Giants
In this era of large-scale spectroscopic stellar surveys, measurements of stellar attributes (“labels,” i.e., parameters and abundances) must be made precise and consistent across surveys. Here, we…
View on IOP Publishing
Copy-move forgery detection based on hybrid features
View via Publisher
FlexPS: Flexible Parallelism Control in Parameter Server Architecture
TLDR
This work proposes a new system, called FlexPS, which introduces a novel multi-stage abstraction to support flexible parallelism control and achieves significant speedups and resource saving compared with the state-of-the-art PS systems such as Petuum and Multiverso.
View via Publisher
Multi-tenant GPU Clusters for Deep Learning Workloads: Analysis and Implications
TLDR
A detailed workload characterization of a two-month long trace from a multi-tenant GPU cluster in a large enterprise is presented and design guidelines pertaining to next-generation cluster schedulers for DNN training workloads are provided.
Tensor and its tucker core: The invariance relationships
TLDR
It is shown that the Tucker core of a tensor retains many properties of the original tensor, including the CANDECOMP/PARAFAC (CP) rank, the border rank,the tensor Schatten quasi norms, and the Z‐eigenvalues when the core tensor is smaller than the original Tensor.
View on Wiley
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License