Feedback Recurrent AutoEncoder (ICASSP2020)
Yang Yang, Guillaume Sautière, J. Jon Ryu, Taco S Cohen
[paper]
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Jie Gui, Zhenan Sun, Yonggang Wen, Dacheng Tao, Jieping Ye
[paper]
Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative
Models is Sensitive to Prior Distribution Choice
[paper]
On Variational Bounds of Mutual Information (ICML2019)
Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker
[paper]
Can We Derive Explicit and Implicit Bias from Corpus?
Bo Wang, Baixiang Xue, Anthony G. Greenwald
[paper]
An Explicitly Relational Neural Network Architecture
Murray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis, David Barrett, Marta Garnelo
[paper]
グラフ信号処理の基礎理論と最近の成果
[slide]
Capsule Routing via Variational Bayes
Fabio De Sousa Ribeiro, Georgios Leontidis, Stefanos Kollias
[paper]
Advanced Super-Resolution using Lossless Pooling Convolutional Networks
Farzad Toutounchi, Ebroul Izquierdo
[paper]
Invertible Residual Networks
Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen
[paper]
On Variational Bounds of Mutual Information (ICML2019)
Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker
[paper]
Learning to Remember Rare Events (ICLR2017)
Łukasz Kaiser, Ofir Nachum, Aurko Roy, Samy Bengio
[paper]
Lifelong Machine Learning and Computer Reading the Web (KDD2016 tutorial)
[link]
Neural Collaborative Subspace Clustering (ICML2019)
Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li
[paper]
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak, Orestis Plevrakis, Nikunj Saunshi
[paper]
A Comprehensive Survey on Graph Neural Networks
Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu
[paper]
Anomaly detection tutorial (ICDM018 tutorial)
[link]
Resampled Priors for Variational Autoencoders
Matthias Bauer, Andriy Mnih
[paper]
Outlier Detection using Generative Models with Theoretical Performance Guarantees
Jirong Yi, Anh Duc Le, Tianming Wang, Xiaodong Wu, Weiyu Xu
[paper]
Discriminator Rejection Sampling
Samaneh Azadi, Catherine Olsson, Trevor Darrell, Ian Goodfellow, Augustus Odena
[paper]
Supervising strong learners by amplifying weak experts
Paul Christiano, Buck Shlegeris, Dario Amodei
[paper]
Differentiable Learning-to-Normalize via Switchable Normalization
Ping Luo, Jiamin Ren, Zhanglin Peng
[paper]
Learning Confidence for Out-of-Distribution Detection in Neural Networks
Terrance DeVries, Graham W. Taylor
[paper]
Neural Vector Spaces for Unsupervised Information Retrieval(TOIS2018)
Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
[paper]
Skill Rating for Generative Models
Catherine Olsson, Surya Bhupatiraju, Tom Brown, Augustus Odena, Ian Goodfellow
[paper]
A Dual Approach to Scalable Verification of Deep Networks (UAI2018 best paper)
Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Sven Gowal, Timothy Mann, Pushmeet Kohli
[paper]
Which Training Methods for GANs do actually Converge? (ICML2018)
[project]
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (ICML2018)
Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, Andrew Rabinovich
[paper]
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (CVPR2018)
Alex Kendall, Yarin Gal, Roberto Cipolla
[paper]
Geometry Score: A Method For Comparing Generative Adversarial Networks (ICML2018)
Valentin Khrulkov, Ivan Oseledets
[paper]
Classification and Geometry of General Perceptual Manifolds
[paper]
Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem
Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
[paper]
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu
[paper]
[slides(ja)]
Deep Energy: Using Energy Functions for Unsupervised Training of DNNs
Alona Golts, Daniel Freedman, Michael Elad
[paper]
To understand deep learning we need to understand kernel learning
Mikhail Belkin, Siyuan Ma, Soumik Mandal
[paper]
Progress & Compress: A scalable framework for continual learning (ICML2018)
Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell
[paper]
Reinforced Co-Training (NAACL2018)
Jiawei Wu, Lei Li, William Yang Wang
[paper]
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
Noam Shazeer, Mitchell Stern
[paper]
Hyperspherical Variational Auto-Encoders
Tim R. Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak
[paper]
InfoVAE: Information Maximizing Variational Autoencoders
Shengjia Zhao, Jiaming Song, Stefano Ermon
[paper]
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery(IPMI2017)
Thomas Schlegl, Philipp Seeböck, Sebastian M. Waldstein, Ursula Schmidt-Erfurth, Georg Langs
[paper]
Graphical Models for Processing Missing Data
Karthika Mohan, Judea Pearl
[paper]
Deep Learning for Sampling from Arbitrary Probability Distributions
Felix Horger, Tobias Würfl, Vincent Christlein, Andreas Maier
[paper]
Learning to Compose Domain-Specific Transformations for Data Augmentation
Alexander J. Ratner, Henry R. Ehrenberg, Zeshan Hussain, Jared Dunnmon, Christopher Ré
[paper]
[slide]
Overcoming catastrophic forgetting with hard attention to the task
Joan Serrà, Dídac Surís, Marius Miron, Alexandros Karatzoglou
[paper]
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results(NIPS2017)
Antti Tarvainen, Harri Valpola
[paper]
[project]
Learning with Imprinted Weights
Hang Qi, Matthew Brown, David G. Lowe
[paper]
MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels
Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, Li Fei-Fei
[paper]
Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications
[paper]
Variational Memory Addressing in Generative Models(NIPS2017)
[paper]
Gradient Episodic Memory for Continual Learning(NIPS2017)
[paper]
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
[paper]
Causal Generative Neural Networks
Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz, Michèle Sebag
[paper]
Deep Hyperspherical Learning
Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, Le Song
[paper]
Metric Learning-based Generative Adversarial Network
Zi-Yi Dou
[paper]
Don't Decay the Learning Rate, Increase the Batch Size
Samuel L. Smith, Pieter-Jan Kindermans, Quoc V. Le
[paper]
Detecting annotation noise in automatically labelled data
[paper]
Mutual Alignment Transfer Learning
Markus Wulfmeier, Ingmar Posner, Pieter Abbeel
[paper]
Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval(ACMMM2017)
Jianan Li (Beijing Institute of Technology); Yunchao Wei (National University of Singapore); Xiaodan Liang (Carnegie Mellon University); Fang Zhao (National University of Singapore); Jianshu Li (National University of Singapore); Tingfa Xu (Beijing Institute of Technology); Jiashi Feng (National University of Singapore)
Region-based Image Retrieval Revisited by Semantic Region Specification and Spatial Relationship Recommendation(ACMMM2017)
Ryota Hinami (The University of Tokyo); Yusuke Matsui (National Institute of Informatics); Shin'Ichi Satoh (National Institute of Informatics)
Robust Imitation of Diverse Behaviors
Ziyu Wang, Josh Merel, Scott Reed, Greg Wayne, Nando de Freitas, Nicolas Heess
paper]
Meta-Learning with Temporal Convolutions
Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel
[paper]
Dual Supervised Learning
Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, Tie-Yan Liu
[paper]
Variance Regularizing Adversarial Learning
Karan Grewal, R Devon Hjelm, Yoshua Bengio
[paper]
Learning by Association - A versatile semi-supervised training method for neural networks
Philip Häusser, Alexander Mordvintsev, Daniel Cremers
[paper]
Learning from Complementary Labels
Takashi Ishida, Gang Niu, Masashi Sugiyama
[paper]
Hyperparameter Optimization: A Spectral Approach
Elad Hazan, Adam Klivans, Yang Yuan
[paper]
Self-Normalizing Neural Networks
Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter
[paper]
The Cramer Distance as a Solution to Biased Wasserstein Gradients
Marc G. Bellemare, Ivo Danihelka, Will Dabney, Shakir Mohamed, Balaji Lakshminarayanan, Stephan Hoyer, Rémi Munos
[paper]
Deep Learning is Robust to Massive Label Noise
David Rolnick, Andreas Veit, Serge Belongie, Nir Shavit
[paper]
Neural Embeddings of Graphs in Hyperbolic Space
Benjamin Paul Chamberlain, James Clough, Marc Peter Deisenroth
[paper]
Continual Learning with Deep Generative Replay
Hanul Shin, Jung Kwon Lee, Jaehong Kim, Jiwon Kim
[paper]
Nonlinear Information Bottleneck
Artemy Kolchinsky, Brendan D. Tracey, David H. Wolpert
[paper]
Grounded Recurrent Neural Networks
Ankit Vani, Yacine Jernite, David Sontag
[paper]
Annealed Generative Adversarial Networks
Arash Mehrjou, Bernhard Schölkopf, Saeed Saremi
[paper]
Real Time Image Saliency for Black Box Classifiers
Piotr Dabkowski, Yarin Gal
[paper]
Cross-lingual Distillation for Text Classification
Ruochen Xu, Yiming Yang
[paper]
Detecting Adversarial Samples Using Density Ratio Estimates
Lovedeep Gondara
[paper]
A recurrent neural network without chaos(ICLR2017)
Thomas Laurent, James von Brecht
[paper]
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
Jiajun Lu, Theerasit Issaranon, David Forsyth
[paper]
Fast Generation for Convolutional Autoregressive Models
Prajit Ramachandran, Tom Le Paine, Pooya Khorrami, Mohammad Babaeizadeh, Shiyu Chang, Yang Zhang, Mark A. Hasegawa-Johnson, Roy H. Campbell, Thomas S. Huang
[paper]
Softmax GAN
Min Lin
[paper]
Overcoming Catastrophic Forgetting in Neural Networks
[paper]
[blog]
[qiita]
Applying Ricci Flow to Manifold Learning
Yangyang Li
[paper]
Improved multitask learning through synaptic intelligence
Friedemann Zenke, Ben Poole, Surya Ganguli
[paper]
Overcoming catastrophic forgetting in neural networks
[paper]
[blog]
Guided Perturbations: Self Corrective Behavior in Convolutional Neural Networks
Swami Sankaranarayanan, Arpit Jain, Ser Nam Lim
[paper]
Deformable Convolutional Networks
Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei
[paper]
Overcoming model simplifications when quantifying predictive uncertainty
George M. Mathews, John Vial
[paper]
On the Expressive Power of Overlapping Operations of Deep Networks
Or Sharir, Amnon Shashua
[paper]
Transfer Learning by Asymmetric Image Weighting for Segmentation across Scanners
Veronika Cheplygina, Annegreet van Opbroek, M. Arfan Ikram, Meike W. Vernooij, Marleen de Bruijne
[paper]
Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths
Yanan Li, Donghui Wang, Huanhang Hu, Yuetan Lin, Yueting Zhuang
[paper]
Universal adversarial perturbations
[paper]
Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
Vatsal Sharan, Gregory Valiant
[paper]
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
Chelsea Finn, Paul Christiano, Pieter Abbeel, Sergey Levine
[paper]
Variational Inference using Implicit Distributions
Ferenc Huszár
[paper]
Depth Creates No Bad Local Minima
Haihao Lu, Kenji Kawaguchi
[paper]
Generative Adversarial Networks in Estimation of Distribution Algorithms for Combinatorial Optimization
Malte Probst
[paper]
Adaptive Neural Networks for Fast Test-Time Prediction
Tolga Bolukbasi, Joseph Wang, Ofer Dekel, Venkatesh Saligrama
[paper]
Dynamic Filter Networks
[slide]
Zero-Shot Learning posed as a Missing Data Problem
Bo Zhao, Botong Wu, Tianfu Wu, Yizhou Wang
[paper]
Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks
Luo Chunjie, Zhan jianfeng, Wang lei, Yang Qiang
[paper]
Dataset Augmentation in Feature Space
Terrance DeVries, Graham W. Taylor
[paper]
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra
[paper]
Harmonic Networks: Deep Translation and Rotation Equivariance
Daniel Worrall Stephan Garbin Daniyar Turmukhambetov Gabriel J. Brostow
[project]
Feature Space Modeling Through Surrogate Illumination
Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret
[paper]
Supervised Learning for Controlled Dynamical System Learning
Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon
[paper]
Parallel Long Short-Term Memory for Multi-stream Classification
Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, Georges Linarès, Renato De Mori
[paper]
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Sergey Ioffe
[paper]
A More General Robust Loss Function
Jonathan T. Barron
[paper]
Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
[paper]
次元削減について
[link]
Language Modeling with Gated Convolutional Networks
Yann N. Dauphin Angela Fan Michael Auli David Grangier (Facebook AI Research)
[paper]
LSTMを凌駕したらしいが果たして・・・
[Project] All Code Implementations for NIPS 2016 papers
[link]
Instance Weighting for Domain Adaptation in NLP(ACL2007)
[paper]
MODE REGULARIZED GENERATIVE ADVERSARIAL NETWORKS
[paper]
IMPROVING GENERATIVE ADVERSARIAL NETWORKS WITH DENOISING FEATURE MATCHING
[paper
Unsupervised Learning of Sentence Representations using Convolutional Neural Networks
Zhe Gan, Yunchen Pu, Ricardo Henao, Chunyuan Li, Xiaodong He, Lawrence Carin
[paper]
A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
Chelsea Finn, Paul Christiano, Pieter Abbeel, Sergey Levine
[paper]
Associative Adversarial Networks
Tarik Arici, Asli Celikyilmaz
[paper]
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Sebastian Nowozin, Botond Cseke, Ryota Tomioka
[paper]
Generative Adversarial Nets from a Density Ratio Estimation Perspective
Masatoshi Uehara, Issei Sato, Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
[paper]
Learning in Implicit Generative Models
Shakir Mohamed, Balaji Lakshminarayanan
[paper]
One-shot Learning with Memory-Augmented Neural Networks
[link]
Building Machines that Imagine and Reason
[link]
##Normalization
##Adversarial Examples
Virtual Adversarial Training for Semi-Supervised Text Classification
[paper]
DISTRIBUTIONAL SMOOTHING WITH VIRTUAL ADVERSARIAL TRAINING(ICLR2016)
[paper]
[code]
猫でも分かるVariational AutoEncoder
[slideshare]