Filters








69,536 Hits in 2.7 sec

Adversarially Learned Inference [article]

Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Olivier Mastropietro, Alex Lamb, Martin Arjovsky, Aaron Courville
2017 arXiv   pre-print
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process.  ...  We illustrate the ability of the model to learn mutually coherent inference and generation networks through the inspections of model samples and reconstructions and confirm the usefulness of the learned  ...  CONCLUSION We introduced the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process.  ... 
arXiv:1606.00704v3 fatcat:kvwvkt427zhzdcbhdxximgx5si

Decomposed Adversarial Learned Inference [article]

Alexander Hanbo Li, Yaqing Wang, Changyou Chen, Jing Gao
2020 arXiv   pre-print
We propose a novel approach, Decomposed Adversarial Learned Inference (DALI), which explicitly matches prior and conditional distributions in both data and code spaces, and puts a direct constraint on  ...  Effective inference for a generative adversarial model remains an important and challenging problem.  ...  To overcome the aforementioned issues, in this paper, we propose a novel approach, decomposed adversarial learned inference (DALI), that integrates efficient inference to GAN and overcomes the limitations  ... 
arXiv:2004.10267v1 fatcat:ly55llcy5bfizkllduhxulf5pe

Generalized Adversarially Learned Inference [article]

Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai
2020 arXiv   pre-print
Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions  ...  Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks.  ...  In the rest of the paper, we refer to our proposed framework as Generalized Adversarially Learned Inference (GALI).  ... 
arXiv:2006.08089v3 fatcat:2ji66xyarzd4peuzetlesk2tei

Hierarchical Adversarially Learned Inference [article]

Mohamed Ishmael Belghazi, Sai Rajeswar, Olivier Mastropietro, Negar Rostamzadeh, Jovana Mitrovic, Aaron Courville
2018 arXiv   pre-print
Both the generative and inference model are trained using the adversarial learning paradigm.  ...  There, we show that the features learned by our model in an unsupervised way outperform the best handcrafted features.  ...  Recent work, known as either ALI or BiGAN , has shown that the adversarial learning paradigm can be extended to incorporate the learning of an inference network.  ... 
arXiv:1802.01071v1 fatcat:infu7db6frgwdbyysjggfnlpoi

Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference [article]

Ruying Bao, Sihang Liang, Qingcan Wang
2018 arXiv   pre-print
FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping between the high-dimensional data space and the low-dimensional semantic space; also  ...  After the bidirectional mapping, the adversarial data can be reconstructed to denoised data, which could be fed into any pre-trained classifier.  ...  Hence, it is natural to extract those semantic features and doing the inference solely based on semantic information.  ... 
arXiv:1805.07862v2 fatcat:rhre6ae4uze2faj4aspmpf2mtu

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference [article]

Louis C. Tiao, Edwin V. Bonilla, Fabio Ramos
2018 arXiv   pre-print
Lastly, we demonstrate that the state-of-the-art cycle-consistent adversarial learning (CYCLEGAN) models can be derived as a special case within our proposed VI framework, thus establishing its connection  ...  We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations  ...  arXiv:1806.01771v3 [stat.ML] 24 Aug 2018 Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference First contribution ( § 2).  ... 
arXiv:1806.01771v3 fatcat:dxqs2zoerjfvtikn7ucedlwchu

Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models [article]

Adarsh K. Jeewajee, Leslie P. Kaelbling
2020 arXiv   pre-print
Instead, we propose an inference-agnostic adversarial training framework which produces an infinitely-large ensemble of graphical models (AGMs).  ...  AGMs perform comparably with EGMs on inference tasks that the latter were specifically optimized for.  ...  [2018] learn tractable graphical models using exact inference through adversarial objectives. Chongxuan et al.  ... 
arXiv:2007.05033v3 fatcat:rnakpa5qajhudmjgzhanvkjhnm

Adversarial Learned Molecular Graph Inference and Generation [article]

Sebastian Pölsterl, Christian Wachinger
2020 arXiv   pre-print
In this work, we propose ALMGIG, a likelihood-free adversarial learning framework for inference and de novo molecule generation that avoids explicitly computing a reconstruction loss.  ...  Our approach extends generative adversarial networks by including an adversarial cycle-consistency loss to implicitly enforce the reconstruction property.  ...  Adversarially Learned Inference We first describe Adversarially Learned Inference with Conditional Entropy (ALICE) [20] , which is at the core of ALMGIG and has not been used for de novo chemical design  ... 
arXiv:1905.10310v2 fatcat:lpephwlkl5cqnklxck44wxygya

Adversary-resilient Distributed and Decentralized Statistical Inference and Machine Learning [article]

Zhixiong Yang, Arpita Gang, Waheed U. Bajwa
2020 arXiv   pre-print
While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual  ...  As a result, we now have a plethora of algorithmic approaches that guarantee robustness of distributed and/or decentralized inference and learning under different adversarial threat models.  ...  As a result, we now have an abundance of algorithmic approaches that guarantee robustness of distributed and/or decentralized inference and learning under different adversarial threat models; see, e.g.  ... 
arXiv:1908.08649v2 fatcat:de356dvwinfv5g5njo64qmzpvi

Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data [article]

Xin Du, Lei Sun, Wouter Duivesteijn, Alexander Nikolaev, Mykola Pechenizkiy
2020 arXiv   pre-print
To overcome these challenges, we propose a neural network framework called Adversarial Balancing-based representation learning for Causal Effect Inference (ABCEI), based on the recent advances in representation  ...  To ensure the identification of CATE, ABCEI uses adversarial learning to balance the distributions of covariates in treatment and control groups in the latent representation space, without any assumption  ...  We propose a novel model: Adversarial Balancing-based representation learning for Causal Effect Inference (ABCEI) with observational data.  ... 
arXiv:1904.13335v3 fatcat:pvsjysmofvfenk3ntzpfuke2a4

HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks [article]

Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber, Radu Teodorescu
2021 arXiv   pre-print
HASI uses the output distribution characteristics of noisy inference compared to a non-noisy reference to detect adversarial inputs.  ...  We show that by carefully injecting noise into the model at inference time, we can differentiate adversarial inputs from benign ones.  ...  Adversarial Attacks Adversarial attacks were first introduced by Szegedy et al. in [32] , which showed that despite the high accuracy of machine learning models, small perturbations to inputs can reliably  ... 
arXiv:2106.05825v3 fatcat:xr2nxttx5nf23f7uh7chhfnk5u

Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference [article]

Xiaocong Chen, Lina Yao, Xianzhi Wang, Aixin Sun, Wenjie Zhang, Quan Z. Sheng
2021 arXiv   pre-print
Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems.  ...  We propose a generative inverse reinforcement learning for user behavioral preference modelling, to address the above issues.  ...  Learning from demonstrations not only avoids the need for inferring a reward function but also reduces computational complexity.  ... 
arXiv:2105.00822v2 fatcat:itlyo4txfjbodp3wyb7oqehg3a

AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning [article]

Jinyuan Jia, Neil Zhenqiang Gong
2020 arXiv   pre-print
We find the minimum noise via adapting existing evasion attacks in adversarial machine learning.  ...  Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g  ...  In adversarial machine learning, this is known as evasion attack.  ... 
arXiv:1805.04810v2 fatcat:ijtcty5pgja6rdep5awx25m2um

Learning and inference on generative adversarial quantum circuits

Jinfeng Zeng, Yufeng Wu, Jin-Guo Liu, Lei Wang, Jiangping Hu
2019 Physical Review A  
We numerically simulate the learning and inference of generative adversarial quantum circuit using the prototypical Bars-and-Stripes dataset.  ...  Generative adversarial quantum circuits is a fresh approach to machine learning which may enjoy the practically useful quantum advantage on near-term quantum devices.  ...  ACKNOWLEDGMENT Learning and inference of the generative adversarial quantum circuits are implemented using Yao.jl  ... 
doi:10.1103/physreva.99.052306 fatcat:7ctrtz4xcjf5npstoxreye7wua

Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges [article]

Jinyuan Jia, Neil Zhenqiang Gong
2019 arXiv   pre-print
Our key observation is that attackers rely on ML classifiers in inference attacks. The adversarial machine learning community has demonstrated that ML classifiers have various vulnerabilities.  ...  As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains.  ...  Defending against Inference Attacks via Adversarial Examples  ... 
arXiv:1909.08526v2 fatcat:6vcswmo5hzbw3fgveamzjcubre
« Previous Showing results 1 — 15 out of 69,536 results