MisGAN is a GAN-based framework for learning from incomplete data. It introduces an auxiliary GAN to model the missingness distribution through a mask generator. The complete data generator is trained adversarially by masking its outputs using generated masks and comparing to real incomplete data masked similarly. Experiments on MNIST, CIFAR-10 and CelebA show MisGAN outperforms baselines and can generate high-quality imputations for missing data. Future work includes extending MisGAN to non-missing completely at random mechanisms and formally evaluating performance.
Deepfake detection is a critical and evolving field aimed at identifying and mitigating the risks associated with manipulated multimedia content created using artificial intelligence (AI) techniques. Deepfakes involve the use of advanced machine learning algorithms, particularly generative models like Generative Adversarial Networks (GANs), to create highly convincing fake videos, audio recordings, or images that can deceive viewers into believing they are genuine.
One prevalent approach to deepfake detection involves leveraging advancements in computer vision and pattern recognition. Researchers and developers employ sophisticated algorithms to analyze various visual and auditory cues that may indicate the presence of deepfake manipulation. For instance, anomalies in facial expressions, inconsistent lighting and shadows, or unnatural lip sync in videos can be indicative of deepfake content. Additionally, deepfake detectors may examine metadata, such as inconsistencies in timestamps or editing artifacts, to identify alterations in the content's authenticity.
Machine learning plays a central role in deepfake detection, with models being trained on diverse datasets that include both authentic and manipulated content. Supervised learning techniques involve training models on labeled datasets, enabling them to recognize patterns associated with deepfake manipulation. Researchers also explore unsupervised and semi-supervised learning methods, allowing detectors to identify anomalies without explicit labels for every training instance.
As the field progresses, deepfake detectors are increasingly adopting advanced neural network architectures to enhance their accuracy. Ensembling multiple models, each specialized in detecting specific types of manipulations, is another strategy employed to improve overall detection performance. Furthermore, the integration of explainable AI techniques enables better understanding of the detection process and provides insights into the features contributing to the decision-making process of the models.
Despite these advancements, deepfake detection remains a challenging task due to the constant evolution of deepfake generation techniques. Adversarial training, where detectors are trained on data that includes adversarial examples, is one method to improve robustness against sophisticated manipulation attempts. Continuous research efforts are required to stay ahead of emerging deepfake technologies and to develop detectors capable of identifying novel manipulation methods.
In conclusion, deepfake detection is a multidimensional challenge that requires a combination of computer vision, machine learning, and data analysis techniques. Researchers and practitioners are actively developing and refining methods to detect manipulated content by examining visual and auditory cues, leveraging machine learning models, and staying vigilant against evolving deepfake technologies. As the threat landscape evolves, ongoing innovati
Variational Autoencoder를 여러 가지 각도에서 이해하기 (Understanding Variational Autoencod...Haezoom Inc.
인공신경망을 이용한 generative model로서 많은 관심을 받고 있는 Variational Autoencoder (VAE)를 보다 잘 이해하기 위해서, 여러 가지 재미있는 관점에서 바라봅니다. VAE 및 머신러닝 일반에 지식을 가지고 있는 청중을 대상으로 진행된 세미나 자료입니다. 현장에서 구두로 설명된 부분은 슬라이드의 회색 박스에 보충설명을 적어두었습니다.
An Extensive Review on Generative Adversarial Networks GAN’sijtsrd
This paper is to provide a high level understanding of Generative Adversarial Networks. This paper will be covering the working of GAN’s by explaining the background idea of the framework, types of GAN’s in the industry, it’s advantages and disadvantages, history of how GAN’s are developed and enhanced along the timeline and some applications where GAN’s outperforms themselves. Atharva Chitnavis | Yogeshchandra Puranik "An Extensive Review on Generative Adversarial Networks (GAN’s)" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42357.pdf Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/42357/an-extensive-review-on-generative-adversarial-networks-gan’s/atharva-chitnavis
Anomaly Detection Using Generative Adversarial Network(GAN)Asha Aher
This presentation covers Anomaly Detection using different GAN architectures. Methodology used in order to check efficiency of GAN in anomaly detection.
Deepfake detection is a critical and evolving field aimed at identifying and mitigating the risks associated with manipulated multimedia content created using artificial intelligence (AI) techniques. Deepfakes involve the use of advanced machine learning algorithms, particularly generative models like Generative Adversarial Networks (GANs), to create highly convincing fake videos, audio recordings, or images that can deceive viewers into believing they are genuine.
One prevalent approach to deepfake detection involves leveraging advancements in computer vision and pattern recognition. Researchers and developers employ sophisticated algorithms to analyze various visual and auditory cues that may indicate the presence of deepfake manipulation. For instance, anomalies in facial expressions, inconsistent lighting and shadows, or unnatural lip sync in videos can be indicative of deepfake content. Additionally, deepfake detectors may examine metadata, such as inconsistencies in timestamps or editing artifacts, to identify alterations in the content's authenticity.
Machine learning plays a central role in deepfake detection, with models being trained on diverse datasets that include both authentic and manipulated content. Supervised learning techniques involve training models on labeled datasets, enabling them to recognize patterns associated with deepfake manipulation. Researchers also explore unsupervised and semi-supervised learning methods, allowing detectors to identify anomalies without explicit labels for every training instance.
As the field progresses, deepfake detectors are increasingly adopting advanced neural network architectures to enhance their accuracy. Ensembling multiple models, each specialized in detecting specific types of manipulations, is another strategy employed to improve overall detection performance. Furthermore, the integration of explainable AI techniques enables better understanding of the detection process and provides insights into the features contributing to the decision-making process of the models.
Despite these advancements, deepfake detection remains a challenging task due to the constant evolution of deepfake generation techniques. Adversarial training, where detectors are trained on data that includes adversarial examples, is one method to improve robustness against sophisticated manipulation attempts. Continuous research efforts are required to stay ahead of emerging deepfake technologies and to develop detectors capable of identifying novel manipulation methods.
In conclusion, deepfake detection is a multidimensional challenge that requires a combination of computer vision, machine learning, and data analysis techniques. Researchers and practitioners are actively developing and refining methods to detect manipulated content by examining visual and auditory cues, leveraging machine learning models, and staying vigilant against evolving deepfake technologies. As the threat landscape evolves, ongoing innovati
Variational Autoencoder를 여러 가지 각도에서 이해하기 (Understanding Variational Autoencod...Haezoom Inc.
인공신경망을 이용한 generative model로서 많은 관심을 받고 있는 Variational Autoencoder (VAE)를 보다 잘 이해하기 위해서, 여러 가지 재미있는 관점에서 바라봅니다. VAE 및 머신러닝 일반에 지식을 가지고 있는 청중을 대상으로 진행된 세미나 자료입니다. 현장에서 구두로 설명된 부분은 슬라이드의 회색 박스에 보충설명을 적어두었습니다.
An Extensive Review on Generative Adversarial Networks GAN’sijtsrd
This paper is to provide a high level understanding of Generative Adversarial Networks. This paper will be covering the working of GAN’s by explaining the background idea of the framework, types of GAN’s in the industry, it’s advantages and disadvantages, history of how GAN’s are developed and enhanced along the timeline and some applications where GAN’s outperforms themselves. Atharva Chitnavis | Yogeshchandra Puranik "An Extensive Review on Generative Adversarial Networks (GAN’s)" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42357.pdf Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/42357/an-extensive-review-on-generative-adversarial-networks-gan’s/atharva-chitnavis
Anomaly Detection Using Generative Adversarial Network(GAN)Asha Aher
This presentation covers Anomaly Detection using different GAN architectures. Methodology used in order to check efficiency of GAN in anomaly detection.
AI Professionals use top machine learning algorithms to automate models that analyze more extensive and complex data which was not possible in older machine learning algos.
With the increase in Internet users the number of malicious users are also growing day-by-day posing a
serious problem in distinguishing between normal and abnormal behavior of users in the network. This
has led to the research area of intrusion detection which essentially analyzes the network traffic and tries
to determine normal and abnormal patterns of behavior.In this paper, we have analyzed the standard
NSL-KDD intrusion dataset using some neural network based techniques for predicting possible
intrusions. Four most effective classification methods, namely, Radial Basis Function Network, Self-
Organizing Map, Sequential Minimal Optimization, and Projective Adaptive Resonance Theory have been
applied. In order to enhance the performance of the classifiers, three entropy based feature selection
methods have been applied as preprocessing of data. Performances of different combinations of classifiers
and attribute reduction methods have also been compared.
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...IJNSA Journal
With the increase in Internet users the number of malicious users are also growing day-by-day posing a serious problem in distinguishing between normal and abnormal behavior of users in the network. This has led to the research area of intrusion detection which essentially analyzes the network traffic and tries to determine normal and abnormal patterns of behavior.In this paper, we have analyzed the standard NSL-KDD intrusion dataset using some neural network based techniques for predicting possible intrusions. Four most effective classification methods, namely, Radial Basis Function Network, SelfOrganizing Map, Sequential Minimal Optimization, and Projective Adaptive Resonance Theory have been applied. In order to enhance the performance of the classifiers, three entropy based feature selection methods have been applied as preprocessing of data. Performances of different combinations of classifiers and attribute reduction methods have also been compared.
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCOREIJCI JOURNAL
Text generation using GAN networks is becoming more effective but still requires new approaches to
achieve stable training and controlled output. Applying feedback score to control text generation is one of
the most important topics in NLP nowadays. Feedback or response is a natural part of conversations and
not only consists of words, but also can take other shapes such as emotions, or other reactions. In dialogue
processes feedback is a factor influencing the next phrase or reaction. Depending on this feedback or
response we correct our possible answers by trying to change the tone, context, or even structure of the
sentences. Applying feedback as part of the GAN model structure will give us new ways to apply feedback
and generate well-controlled outputs with defined scores which is very important in real-world
applications and systems. With GAN networks and their instability in training and unique architecture, it
becomes trickier and requires new ways of solving this problem. The matter of feedback usages for text
generation task using GAN networks we will review in this paper and experiment with integrating score
values into GAN's generator model layers.
Progress of Machine Learning in the Field of Intrusion Detection Systemsijcisjournal
With the growth in the use of the Internet and local area networks, malicious attacks and intrusions into
computer systems are increasing. Implementing intrusion detection systems have become extremely
important to help maintain good network security. Support vector machines (SVMs), a classic pattern
recognition tool, have been widely used in intrusion detection. They can handle very large data with high
efficiency, are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model
enriched with a Gaussian kernel function based on the features of the training data for intrusion detection.
The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection
efficiency and false alarm rate, which can give better coverage and make detection more efficient.
11421ijcPROGRESS OF MACHINE LEARNING IN THE FIELD OF INTRUSION DETECTION SYST...ijcisjournal
With the growth in the use of the Internet and local area networks, malicious attacks and intrusions into computer systems are increasing. Implementing intrusion detection systems have become extremely important to help maintain good network security. Support vector machines (SVMs), a classic pattern recognition tool, have been widely used in intrusion detection. They can handle very large data with high efficiency, are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model enriched with a Gaussian kernel function based on the features of the training data for intrusion detection. The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection efficiency and false alarm rate, which can give better coverage and make detection more efficient.
Today, we can see in machine learning that methods and models from one field may carry out operations from another. For instance, some computer vision-related tasks can be completed by models that are primarily geared toward natural language processing. We will talk about a technique that can be used from NLP to computer vision in this essay. Masked Image Modelling is the name we can give it when we apply it to Image Masking computer vision applications. We'll make an effort to comprehend how this technology functions and some of its key applications. The following list includes the main points that will be covered in this article.
basics of GAN neural network
GAN is a advanced tech in area of neural networks which will help to generate new data . This new data will be developed based over the past experiences and raw data.
Abstract: Detection of fake news based on deep learning techniques is a major issue used to mislead people. For
the experiments, several types of datasets, models, and methodologies have been used to detect fake news. Also,
most of the datasets contain text id, tweets id, and user-based id and user-based features. To get the proper results
and accuracy various models like CNN (Convolution neural network), DEEP CNN, and LSTM (Long short-term
memory) are used
AN IMPROVED CTGAN FOR DATA PROCESSING METHOD OF IMBALANCED DISK FAILUREIJCI JOURNAL
To address the problem of insufficient failure data generated by disks and the imbalance between the number of normal and failure data. The existing Conditional Tabular Generative Adversarial Networks(CTGAN) deep learning methods have been proven to be effective in solving imbalance disk failure data. But CTGAN cannot learn the internal information of disk failure data very well. In this paper,
a fault diagnosis method based on improved CTGAN, a classifier for specific category discrimination is added and a discriminator generate adversarial network based on residual network is proposed. We named it Residual Conditional Tabular Generative Adversarial Networks (RCTGAN). Firstly, to enhance the stability of system a residual network is utilized. RCTGAN uses a small amount of real failure data to synthesize fake fault data; Then, the synthesized data is mixed with the real data to balance the amount of normal and failure data; Finally, four classifier (multilayer perceptron, support vector machine, decision tree, random forest) models are trained using the balanced data set, and the performance of the models is evaluated using G-mean. The experimental results show that the data synthesized by the RCTGAN can
further improve the fault diagnosis accuracy of the classifier.
Similar to [Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversarial Networks (ICLR'19) (20)
Show drafts
volume_up
Empowering the Data Analytics Ecosystem: A Laser Focus on Value
The data analytics ecosystem thrives when every component functions at its peak, unlocking the true potential of data. Here's a laser focus on key areas for an empowered ecosystem:
1. Democratize Access, Not Data:
Granular Access Controls: Provide users with self-service tools tailored to their specific needs, preventing data overload and misuse.
Data Catalogs: Implement robust data catalogs for easy discovery and understanding of available data sources.
2. Foster Collaboration with Clear Roles:
Data Mesh Architecture: Break down data silos by creating a distributed data ownership model with clear ownership and responsibilities.
Collaborative Workspaces: Utilize interactive platforms where data scientists, analysts, and domain experts can work seamlessly together.
3. Leverage Advanced Analytics Strategically:
AI-powered Automation: Automate repetitive tasks like data cleaning and feature engineering, freeing up data talent for higher-level analysis.
Right-Tool Selection: Strategically choose the most effective advanced analytics techniques (e.g., AI, ML) based on specific business problems.
4. Prioritize Data Quality with Automation:
Automated Data Validation: Implement automated data quality checks to identify and rectify errors at the source, minimizing downstream issues.
Data Lineage Tracking: Track the flow of data throughout the ecosystem, ensuring transparency and facilitating root cause analysis for errors.
5. Cultivate a Data-Driven Mindset:
Metrics-Driven Performance Management: Align KPIs and performance metrics with data-driven insights to ensure actionable decision making.
Data Storytelling Workshops: Equip stakeholders with the skills to translate complex data findings into compelling narratives that drive action.
Benefits of a Precise Ecosystem:
Sharpened Focus: Precise access and clear roles ensure everyone works with the most relevant data, maximizing efficiency.
Actionable Insights: Strategic analytics and automated quality checks lead to more reliable and actionable data insights.
Continuous Improvement: Data-driven performance management fosters a culture of learning and continuous improvement.
Sustainable Growth: Empowered by data, organizations can make informed decisions to drive sustainable growth and innovation.
By focusing on these precise actions, organizations can create an empowered data analytics ecosystem that delivers real value by driving data-driven decisions and maximizing the return on their data investment.
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Data Centers - Striving Within A Narrow Range - Research Report - MCG - May 2...pchutichetpong
M Capital Group (“MCG”) expects to see demand and the changing evolution of supply, facilitated through institutional investment rotation out of offices and into work from home (“WFH”), while the ever-expanding need for data storage as global internet usage expands, with experts predicting 5.3 billion users by 2023. These market factors will be underpinned by technological changes, such as progressing cloud services and edge sites, allowing the industry to see strong expected annual growth of 13% over the next 4 years.
Whilst competitive headwinds remain, represented through the recent second bankruptcy filing of Sungard, which blames “COVID-19 and other macroeconomic trends including delayed customer spending decisions, insourcing and reductions in IT spending, energy inflation and reduction in demand for certain services”, the industry has seen key adjustments, where MCG believes that engineering cost management and technological innovation will be paramount to success.
MCG reports that the more favorable market conditions expected over the next few years, helped by the winding down of pandemic restrictions and a hybrid working environment will be driving market momentum forward. The continuous injection of capital by alternative investment firms, as well as the growing infrastructural investment from cloud service providers and social media companies, whose revenues are expected to grow over 3.6x larger by value in 2026, will likely help propel center provision and innovation. These factors paint a promising picture for the industry players that offset rising input costs and adapt to new technologies.
According to M Capital Group: “Specifically, the long-term cost-saving opportunities available from the rise of remote managing will likely aid value growth for the industry. Through margin optimization and further availability of capital for reinvestment, strong players will maintain their competitive foothold, while weaker players exit the market to balance supply and demand.”
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...2023240532
Quantitative data Analysis
Overview
Reliability Analysis (Cronbach Alpha)
Common Method Bias (Harman Single Factor Test)
Frequency Analysis (Demographic)
Descriptive Analysis
Explore our comprehensive data analysis project presentation on predicting product ad campaign performance. Learn how data-driven insights can optimize your marketing strategies and enhance campaign effectiveness. Perfect for professionals and students looking to understand the power of data analysis in advertising. for more details visit: https://bostoninstituteofanalytics.org/data-science-and-artificial-intelligence/
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversarial Networks (ICLR'19)
1. MisGAN
Learning from Incomplete Data with Generative Adversarial Networks
Steven Cheng-Xian Li
University of Massachusetts Amherst
Jihoo Kim
datartist@hanyang.ac.kr
Dept. of Computer and Software, Hanyang University
ICLR’19
2. Abstract
GANs provides an effective way to model complex distributions.
But, typical GANs require full-observed data during training.
In this paper, we present a GAN-based framework for learning from complex, high-
dimensional incomplete data
The proposed framework learns a complete data generator
along with a mask generator that models the missing data distribution.
We evaluate the proposed framework under the MCAR assumption.
3. 1. Introduction
Unlike likelihood-based methods, GANs is an implicit probabilistic models
which represent a probability distribution through a generator
that learns to directly produce samples from the desired distribution.
GANs have been shown to be very successful in a range of applications
- Generating photorealistic images (2018)
- Image inpainting (2016, 2017)
Training GANs normally requires access to a large collection of fully-observed data.
However, it is not always possible to obtain a large amount of full-observed data.
4. 1. Introduction
The generative process for incompletely observed data (2014, Little & Rubin)
the observed elements of x
the missing according to the mask m
the unknown parameters
of the mask distribution
the unknown parameters
of the data distribution
a binary mask that determines
which entries in x to reveal
a complete data vector
5. 1. Introduction
The unknown parameters are estimated by maximizing the following marginal likelihood.
Little & Rubin (2014) characterize the missing data mechanism
in terms of independence between the complete data x, and the masks m.
①
②
③
6. 1. Introduction
Most work on incomplete data assumes MCAR or MAR since under these assumptions
can be factorized into .
→ The missing data mechanism can be ignored when learning the data generating model
while yielding correct estimates for θ.
When does not admit efficient marginalization over , estimation of θ is usually
performed by maximizing a variational lower bound
7. 1. Introduction
The primary contribution of this paper is the development of a GAN-based framework for
learning high-dimensional data distributions in the presence of incomplete observations.
Our framework introduces an auxiliary GAN for learning a mask distribution to model
the missingness.
The masks are used to “mask” generated complete data by filling the indicated missing
entries with a constant value.
The complete data generator is trained so that the resulting masked data are
indistinguishable from real incomplete data that are masked similarly.
8. 1. Introduction
Our framework builds on the ideas of AmbientGAN (2018).
AmbientGAN modifies the discriminator of a GAN to distinguish corrupted real samples
from corrupted generated samples under a range of corruption processes.
Missing data can be seen as a special type of corruption.
AmbientGAN assumes the measurement process is known only by a few parameters,
which is not the case in general missing data problems.
9. We provide empirical evidence that the proposed framework is able to effectively learn
complex, high-dimensional data distributions from highly incomplete data.
We further show how the architecture can be used to generate high-quality imputations.
1. Introduction
10. 1 , is observed.
2. MisGAN: A GAN for Missing Data
incomplete data
a partially-observed data vector
a corresponding mask
0 , is missing and contain arbitrary value that we should ignore.
It leads to a cleaner description of the proposed MisGAN.
It suggests how MisGAN can be implemented efficiently.
Instead of …
11. Two key ideas…
1. We explicitly model the missing data process using a mask generator.
Since the masks in the incomplete dataset are fully observed, we can estimate their distribution.
2. We train the complete data generator adversarially by masking its outputs using generated
masks and , and comparing to real incomplete data that are similarly masked by .
2. MisGAN: A GAN for Missing Data
Masking operator that fills in missing entries with a constant value .
12. 2. MisGAN: A GAN for Missing Data
We use two generator-discriminator pairs
We focus on MCAR, where the two generators are independent of each other
and have their own noise distributions
Loss function for the masks
Loss function for the data
Fake MaskReal Mask
Fake DataReal Data
13. 2. MisGAN: A GAN for Missing Data
We optimize the generators and the discriminators according to the following objectives
Loss function for the masks
Loss function for the data
The losses above follow the Wasserstein GAN formulation (Arjovsky, 2017)
coefficient
We find that choosing a small value
such as 𝜶 = 𝟎. 𝟐 improves performance
15. Wasserstein GAN (Arjovsky, 2017) Facebook AI Research
Wasserstein GAN (WGAN) proposes a new cost function
using Wasserstein distance that has a smoother gradient everywhere.
Arjovsky et al 2017 wrote a paper to illustrate the GAN problem mathematically.
17. 2. MisGAN: A GAN for Missing Data
The data discriminator takes as input the masked samples as if the data are fully-observed.
This allows us to use any existing architecture designed for complete data.
The masks are binary. Discrete data generating processes have zero gradient almost everywhere.
To carry out gradient-based training for GANs, we relax the output of the mask generator .
The discriminator in MisGAN is unaware of which entries are missing in the masked input samples,
and does not even need to know which value is used for masking. (In next section, theoretical analysis)
Note that…
19. 3. Theoretical Results
Two important questions
Does the choice of the filled-in value
affect the ability to recover the data distribution?
Does information about the location of missing values
affect the ability to recover the data distribution?
Q1.
Q2.
24. 4. Missing Data Imputation
We show how to impute missing data according to
by equipping MisGAN with an imputer accompanied by a corresponding discriminator .
Loss function for the masks
Loss function for the data
Loss function for the imputer
noise distribution
𝜶 = 𝟎. 𝟐
𝜷 = 𝟎. 𝟏
This encourages the generated masks
to match the distribution of the real masks
and the masked generated complete samples
to match masked real data.
This encourages the generated complete data
to match the distribution of the imputed real data
In addition to having the masked generated data
match the masked real data.
25. 4. Missing Data Imputation
We can also train a stand-alone imputer using only
with a pre-trained data generator .
Moreover, it is also possible to train the imputer to target a different missing distribution
with a pre-trained data generator alone without access to the original (incomplete) training data
27. 5. Experiments
Data
Missing data
distributions
Evaluation
metric
MNIST
CIFAR-10
CelebA
28x28 handwritten digits images
32x32 color images from 10 classes
64x64 face images (202,599)
The range of pixel values
is rescaled to
Square
observation
Dropout
Variable-size
rectangular
observation
All pixels are missing except for a square
occurring at a random location on the image
Each pixel is independently missing
according to a Bernoulli distribution
All pixels are missing except for a rectangular observed region
(width and height are drawn from 25% to 75% o the image length)
(Heusel, 2017)
28. 5. Experiments
1. Architectures
2. Baseline
3. Results
MisGAN with convolutional networks – DCGAN (Radford, 2015)
MisGAN with fully connected networksFC-MisGAN
Conv-MisGAN
ConvAC
The generative convolutional arithmetic circuit (Sharir, 2016)
→ capable of learning from large-scale incomplete data
Figure 3
Figure 4
Figure 5
Figure 6
5.1 Empirical Study of MisGAN on MNIST
Next slides...
30. 5. Experiments 5.1 Empirical Study of MisGAN on MNIST
MisGAN outperforms ConvAC
Data samples generated by Conv-MisGAN
Mask samples generated by Conv-MisGAN
Data samples generated by MisGAN
Variable-size
Square
31. 5. Experiments
4. Ablation study
5.1 Empirical Study of MisGAN on MNIST
We point out that the mask discriminator in MisGAN is important for learning the correct distribution.
Two failure cases of AmbientGAN, which is essentially equivalent to a MisGAN without the mask discriminator.
Generated data samplesGenerated mask samples Generated data samples Generated mask samples
rescale
32. 5. Experiments 5.1 Empirical Study of MisGAN on MNIST
5. Missing data imputation
Inside of box → observed pixels
Outside of box → generated pixels Each row → same incomplete input
The imputer can produce a variety of different imputed results
33. 5. Experiments 5.2 Quantitative Evaluation
1. Baselines
3. Architecture
2. Evaluation of
imputation
4. Results
We focus on evaluating MisGAN on the missing data imputation task
zero/mean imputation
matrix factorization
GAIN (Generative Adversarial Imputation Network)
FID between the imputed data and the original fully-observed data
For MNIST → Fully-connected imputer network
For CIFAR-10 and CelebA → Five-layer U-Net architecture (Ronneberger, 2015)
Next slides...
34. 5. Experiments 5.2 Quantitative Evaluation
MisGAN consistently outperforms other methods in all cases, especially under high missing rates.
Training MisGAN is more stable than training GAIN.
35. 6. Discussion and Future Work
This work presents and evaluates a high flexible framework for learning
standard GAN data generators in the presence of missing data.
We only focus on the MCAR case in this work.
MisGAN can be easily extended to cases both MAR and NMAR.
We have tried the modified architecture and it showed similar results.
This suggests that the extra dependencies may not adversely affect learnability.
We leave the formal evaluation of this modified framework for future work.