Deep Learning
Zero-shot Knowledge Transfer via Adversarial Belief Matching
Paul Micaelli, Amos J. Storkey
We propose a novel method which trains a student to match the predictions of its teacher without using any data or metadata. We achieve this by training an adversarial generator to search for images on which the student poorly matches the teacher, and then using them to train the student.
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, Been Kim
Neural Information Processing Systems http://nips.cc/
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
Minshuo Chen, Haoming Jiang, Wenjing Liao, Tuo Zhao
Deep neural networks have revolutionized many real world applications, due to their flexibility in data fitting and accurate predictions for unseen data.
Semi-Implicit Graph Variational Auto-Encoders
Arman Hasanzadeh, Ehsan Hajiramezanali, Krishna Narayanan, Nick Duffield, Mingyuan Zhou, Xiaoning Qian
Semi-implicit graph variational auto-encoder (SIG-V AE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data.
Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
Ximei Wang, Ying Jin, Mingsheng Long, Jianmin Wang, Michael I. Jordan
Pre-trained DNNs also show strong transferability when fine-tuned to other labeled datasets.
Differential Privacy Has Disparate Impact on Model Accuracy
Eugene Bagdasaryan, Omid Poursaeed, Vitaly Shmatikov
The cost of differential privacy is a reduction in the model's accuracy.
On the Downstream Performance of Compressed Word Embeddings
Avner May, Jian Zhang, Tri Dao, Christopher Rรฉ
Neural Information Processing Systems http://nips.cc/
Experience Replay for Continual Learning
David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, Gregory Wayne
Neural Information Processing Systems http://nips.cc/
Neural Diffusion Distance for Image Segmentation
The network is a differentiable deep architecture consisting of feature extraction and diffusion distance modules for computing diffusion distance on image by end-to-end training. We design low resolution kernel matching loss and high resolution segment matching loss to enforce the network's output to be consistent with human-labeled image segments.