February 1, 2020

3149 words 15 mins read

Paper Group AWR 274

DeepView: Visualizing the behavior of deep neural networks in a part of the data space. Poisoning Attacks with Generative Adversarial Nets. QPyTorch: A Low-Precision Arithmetic Simulation Framework. Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics. Architectural Middleware that Supports Building High-performance, …

DeepView: Visualizing the behavior of deep neural networks in a part of the data space


Title	DeepView: Visualizing the behavior of deep neural networks in a part of the data space
Authors	Alexander Schulz, Fabian Hinder, Barbara Hammer
Abstract	Machine learning models using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, mostly methods have been proposed to investigate the decision of the model for a single given input datum. In this paper, we propose to visualize a part of the decision function of a deep neural network together with a part of the data set in two dimensions with discriminative dimensionality reduction. This enables us to inspect how different properties of the data are treated by the model, such as multimodality, label noise or biased data. Further, the presented approach is complementary to the mentioned interpretation methods from the literature and hence might be even more useful in combination with those.
Tasks	Dimensionality Reduction
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09154v1
PDF	https://arxiv.org/pdf/1909.09154v1.pdf
PWC	https://paperswithcode.com/paper/deepview-visualizing-the-behavior-of-deep
Repo	https://github.com/LucaHermes/DeepView
Framework	pytorch

Poisoning Attacks with Generative Adversarial Nets


Title	Poisoning Attacks with Generative Adversarial Nets
Authors	Luis Muñoz-González, Bjarne Pfitzner, Matteo Russo, Javier Carnerero-Cano, Emil C. Lupu
Abstract	Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm’s performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i.e. samples that look like genuine data points but that degrade the classifier’s accuracy when used for training. We propose a Generative Adversarial Net with three components: generator, discriminator, and the target classifier. This approach allows us to model naturally the detectability constrains that can be expected in realistic attacks and to identify the regions of the underlying data distribution that can be more vulnerable to data poisoning. Our experimental evaluation shows the effectiveness of our attack to compromise machine learning classifiers, including deep networks.
Tasks	data poisoning
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07773v2
PDF	https://arxiv.org/pdf/1906.07773v2.pdf
PWC	https://paperswithcode.com/paper/poisoning-attacks-with-generative-adversarial
Repo	https://github.com/lmunoz-gonzalez/Poisoning-Attacks-with-Back-gradient-Optimization
Framework	none

QPyTorch: A Low-Precision Arithmetic Simulation Framework


Title	QPyTorch: A Low-Precision Arithmetic Simulation Framework
Authors	Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa
Abstract	Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effects of quantization while avoiding the substantial overhead of building specific hardware. To support this empirical research, we introduce QPyTorch, a low-precision arithmetic simulation framework. Built natively in PyTorch, QPyTorch provides a convenient interface that minimizes the efforts needed to reliably convert existing codes to study low-precision training. QPyTorch is general, and supports a variety of combinations of precisions, number formats, and rounding options. Additionally, it leverages an efficient fused-kernel approach to reduce simulator overhead, which enables simulation of large-scale, realistic problems. QPyTorch is publicly available at https://github.com/Tiiiger/QPyTorch.
Tasks	Quantization
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04540v1
PDF	https://arxiv.org/pdf/1910.04540v1.pdf
PWC	https://paperswithcode.com/paper/qpytorch-a-low-precision-arithmetic
Repo	https://github.com/Tiiiger/QPyTorch
Framework	pytorch

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics


Title	Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
Authors	Yuxin Ma, Tiankai Xie, Jundong Li, Ross Maciejewski
Abstract	Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks. As the deployment of artificial intelligence technologies becomes ubiquitous, it is unsurprising that adversaries have begun developing methods to manipulate machine learning models to their advantage. While the visual analytics community has developed methods for opening the black box of machine learning models, little work has focused on helping the user understand their model vulnerabilities in the context of adversarial attacks. In this paper, we present a visual analytics framework for explaining and exploring model vulnerabilities to adversarial attacks. Our framework employs a multi-faceted visualization scheme designed to support the analysis of data poisoning attacks from the perspective of models, data instances, features, and local structures. We demonstrate our framework through two case studies on binary classifiers and illustrate model vulnerabilities with respect to varying attack strategies.
Tasks	data poisoning
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07296v4
PDF	https://arxiv.org/pdf/1907.07296v4.pdf
PWC	https://paperswithcode.com/paper/explaining-vulnerabilities-to-adversarial
Repo	https://github.com/VADERASU/visual-analytics-adversarial-attacks
Framework	none

Architectural Middleware that Supports Building High-performance, Scalable, Ubiquitous, Intelligent Personal Assistants


Title	Architectural Middleware that Supports Building High-performance, Scalable, Ubiquitous, Intelligent Personal Assistants
Authors	Oscar J. Romero
Abstract	Intelligent Personal Assistants (IPAs) are software agents that can perform tasks on behalf of individuals and assist them on many of their daily activities. IPAs capabilities are expanding rapidly due to the recent advances on areas such as natural language processing, machine learning, artificial cognition, and ubiquitous computing, which equip the agents with competences to understand what users say, collect information from everyday ubiquitous devices (e.g., smartphones, wearables, tablets, laptops, cars, household appliances, etc.), learn user preferences, deliver data-driven search results, and make decisions based on user’s context. Apart from the inherent complexity of building such IPAs, developers and researchers have to address many critical architectural challenges (e.g., low-latency, scalability, concurrency, ubiquity, code mobility, interoperability, support to cognitive services and reasoning, to name a few.), thereby diverting them from their main goal: building IPAs. Thus, our contribution in this paper is twofold: 1) we propose an architecture for a platform-agnostic, high-performance, ubiquitous, and distributed middleware that alleviates the burdensome task of dealing with low-level implementation details when building IPAs by adding multiple abstraction layers that hide the underlying complexity; and 2) we present an implementation of the middleware that concretizes the aforementioned architecture and allows the development of high-level capabilities while scaling the system up to hundreds of thousands of IPAs with no extra effort. We demonstrate the powerfulness of our middleware by analyzing software metrics for complexity, effort, performance, cohesion and coupling when developing a conversational IPA.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02068v1
PDF	https://arxiv.org/pdf/1906.02068v1.pdf
PWC	https://paperswithcode.com/paper/architectural-middleware-that-supports
Repo	https://github.com/ojrlopez27/multiuser-framework
Framework	none

Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions


Title	Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions
Authors	Anh Duc Le, Bipin Indurkhya, Masaki Nakagawa
Abstract	Recognition of Handwritten Mathematical Expressions (HMEs) is a challenging problem because of the ambiguity and complexity of two-dimensional handwriting. Moreover, the lack of large training data is a serious issue, especially for academic recognition systems. In this paper, we propose pattern generation strategies that generate shape and structural variations to improve the performance of recognition systems based on a small training set. For data generation, we employ the public databases: CROHME 2014 and 2016 of online HMEs. The first strategy employs local and global distortions to generate shape variations. The second strategy decomposes an online HME into sub-online HMEs to get more structural variations. The hybrid strategy combines both these strategies to maximize shape and structural variations. The generated online HMEs are converted to images for offline HME recognition. We tested our strategies in an end-to-end recognition system constructed from a recent deep learning model: Convolutional Neural Network and attention-based encoder-decoder. The results of experiments on the CROHME 2014 and 2016 databases demonstrate the superiority and effectiveness of our strategies: our hybrid strategy achieved classification rates of 48.78% and 45.60%, respectively, on these databases. These results are competitive compared to others reported in recent literature. Our generated datasets are openly available for research community and constitute a useful resource for the HME recognition research in future.
Tasks
Published	2019-01-21
URL	http://arxiv.org/abs/1901.06763v1
PDF	http://arxiv.org/pdf/1901.06763v1.pdf
PWC	https://paperswithcode.com/paper/pattern-generation-strategies-for-improving
Repo	https://github.com/ducanh841988/Artificial-Online-Handwritten-Mathematical-Expressions
Framework	none

Deep autoregressive models for the efficient variational simulation of many-body quantum systems


Title	Deep autoregressive models for the efficient variational simulation of many-body quantum systems
Authors	Or Sharir, Yoav Levine, Noam Wies, Giuseppe Carleo, Amnon Shashua
Abstract	Artificial Neural Networks were recently shown to be an efficient representation of highly-entangled many-body quantum states. In practical applications, neural-network states inherit numerical schemes used in Variational Monte Carlo, most notably the use of Markov-Chain Monte-Carlo (MCMC) sampling to estimate quantum expectations. The local stochastic sampling in MCMC caps the potential advantages of neural networks in two ways: (i) Its intrinsic computational cost sets stringent practical limits on the width and depth of the networks, and therefore limits their expressive capacity; (ii) Its difficulty in generating precise and uncorrelated samples can result in estimations of observables that are very far from their true value. Inspired by the state-of-the-art generative models used in machine learning, we propose a specialized Neural Network architecture that supports efficient and exact sampling, completely circumventing the need for Markov Chain sampling. We demonstrate our approach for two-dimensional interacting spin models, showcasing the ability to obtain accurate results on larger system sizes than those currently accessible to neural-network quantum states.
Tasks
Published	2019-02-11
URL	https://arxiv.org/abs/1902.04057v3
PDF	https://arxiv.org/pdf/1902.04057v3.pdf
PWC	https://paperswithcode.com/paper/deep-autoregressive-models-for-the-efficient
Repo	https://github.com/HUJI-Deep/FlowKet
Framework	tf

Inception-inspired LSTM for Next-frame Video Prediction


Title	Inception-inspired LSTM for Next-frame Video Prediction
Authors	Matin Hosseini, Anthony S. Maida, Majid Hosseini, Gottumukkala Raju
Abstract	The problem of video frame prediction has received much interest due to its relevance to many computer vision applications such as autonomous vehicles or robotics. Supervised methods for video frame prediction rely on labeled data, which may not always be available. In this paper, we provide a novel unsupervised deep-learning method called Inception-based LSTM for video frame prediction. The general idea of inception networks is to implement wider networks instead of deeper networks. This network design was shown to improve the performance of image classification. The proposed method is evaluated on both Inception-v1 and Inception-v2 structures. The proposed Inception LSTM methods are compared with convolutional LSTM when applied using PredNet predictive coding framework for both the KITTI and KTH data sets. We observed that the Inception based LSTM outperforms the convolutional LSTM. Also, Inception LSTM has better prediction performance compared to Inception v2 LSTM. However, Inception v2 LSTM has a lower computational cost compared to Inception LSTM.
Tasks	Autonomous Vehicles, Image Classification, Video Prediction
Published	2019-08-28
URL	https://arxiv.org/abs/1909.05622v1
PDF	https://arxiv.org/pdf/1909.05622v1.pdf
PWC	https://paperswithcode.com/paper/inception-inspired-lstm-for-next-frame-video
Repo	https://github.com/matinhosseiny/Inception-inspired-LSTM-for-Video-frame-Prediction
Framework	none

Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network


Title	Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network
Authors	Chaojie Zhao, Peng Zhang, Jian Zhu, Chengrui Wu, Huaimin Wang, Kele Xu
Abstract	A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory (ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network (3DCNN) in predicting the 9\textsuperscript{th} frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Further tests reveal that ConvLSTM can also learn to predict tongue movements in more distant frames beyond the immediately following frames. Our codes are available at: https://github.com/shuiliwanwu/ConvLstm-ultrasound-videos.
Tasks	motion prediction
Published	2019-02-19
URL	http://arxiv.org/abs/1902.06927v1
PDF	http://arxiv.org/pdf/1902.06927v1.pdf
PWC	https://paperswithcode.com/paper/predicting-tongue-motion-in-unlabeled
Repo	https://github.com/shuiliwanwu/ConvLstm-ultrasound-videos
Framework	pytorch

Task-Oriented Optimal Sequencing of Visualization Charts


Title	Task-Oriented Optimal Sequencing of Visualization Charts
Authors	Danqing Shi, Yang Shi, Xinyue Xu, Nan Chen, Siwei Fu, Hongjin Wu, Nan Cao
Abstract	A chart sequence is used to describe a series of visualization charts generated in the exploratory analysis by data analysts. It provides information details in each chart as well as a logical relationship among charts. While existing research targets on generating chart sequences that match human’s perceptions, little attention has been paid to formulate task-oriented connections between charts in a chart design space. We present a novel chart sequencing method based on reinforcement learning to capture the connections between charts in the context of three major analysis tasks, including correlation analysis, anomaly detection, and cluster analysis. The proposed method formulates a chart sequencing procedure as an optimization problem, which seeks an optimal policy to sequencing charts for the specific analysis task. In our method, a novel reward function is introduced, which takes both the analysis task and the factor of human cognition into consideration. We conducted one case study and two user studies to evaluate the effectiveness of our method under the application scenarios of visualization demonstration, sequencing charts for reasoning analysis results, and making a chart design choice. The study results showed the power of our method.
Tasks	Anomaly Detection
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02502v1
PDF	https://arxiv.org/pdf/1908.02502v1.pdf
PWC	https://paperswithcode.com/paper/task-oriented-optimal-sequencing-of
Repo	https://github.com/mstaniak/autoEDA-resources
Framework	none

An Unsupervised Framework for Comparing Graph Embeddings


Title	An Unsupervised Framework for Comparing Graph Embeddings
Authors	Bogumil Kaminski, Pawel Pralat, Francois Theberge
Abstract	Graph embedding is a transformation of vertices of a graph into set of vectors. Good embeddings should capture the graph topology, vertex-to-vertex relationship, and other relevant information about graphs, subgraphs, and vertices. If these objectives are achieved, they are meaningful, understandable, and compressed representations of networks. They also provide more options and tools for data scientists as machine learning on graphs is still quite limited. Finally, vector operations are simpler and faster than comparable operations on graphs. The main challenge is that one needs to make sure that embeddings well describe the properties of the graphs. In particular, the decision has to be made on the embedding dimensionality which highly impacts the quality of an embedding. As a result, selecting the best embedding is a challenging task and very often requires domain experts. In this paper, we propose a ``divergence score’’ that can be assign to various embeddings to distinguish good ones from bad ones. This general framework provides a tool for an unsupervised graph embedding comparison. In order to achieve it, we needed to generalize the well-known Chung-Lu model to incorporate geometry which is interesting on its own rights. In order to test our framework, we did a number of experiments with synthetic networks as well as real-world networks, and various embedding algorithms. \|
Tasks	Graph Embedding
Published	2019-05-29
URL	https://arxiv.org/abs/1906.04562v1
PDF	https://arxiv.org/pdf/1906.04562v1.pdf
PWC	https://paperswithcode.com/paper/an-unsupervised-framework-for-comparing-graph
Repo	https://github.com/ftheberge/Comparing_Graph_Embeddings
Framework	none

Compositional Fairness Constraints for Graph Embeddings


Title	Compositional Fairness Constraints for Graph Embeddings
Authors	Avishek Joey Bose, William L. Hamilton
Abstract	Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional—meaning that it can flexibly accommodate different combinations of fairness constraints during inference. For instance, in the context of social recommendations, our framework would allow one user to request that their recommendations are invariant to both their age and gender, while also allowing another user to request invariance to just their age. Experiments on standard knowledge graph and recommender system benchmarks highlight the utility of our proposed framework.
Tasks	Graph Embedding, Recommendation Systems
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10674v4
PDF	https://arxiv.org/pdf/1905.10674v4.pdf
PWC	https://paperswithcode.com/paper/compositional-fairness-constraints-for-graph
Repo	https://github.com/joeybose/Flexible-Fairness-Constraints
Framework	pytorch

Auto-completion for Data Cells in Relational Tables


Title	Auto-completion for Data Cells in Relational Tables
Authors	Shuo Zhang, Krisztian Balog
Abstract	We address the task of auto-completing data cells in relational tables. Such tables describe entities (in rows) with their attributes (in columns). We present the CellAutoComplete framework to tackle several novel aspects of this problem, including: (i) enabling a cell to have multiple, possibly conflicting values, (ii) supplementing the predicted values with supporting evidence, (iii) combining evidence from multiple sources, and (iv) handling the case where a cell should be left empty. Our framework makes use of a large table corpus and a knowledge base as data sources, and consists of preprocessing, candidate value finding, and value ranking components. Using a purpose-built test collection, we show that our approach is 40% more effective than the best baseline.
Tasks
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03443v2
PDF	https://arxiv.org/pdf/1909.03443v2.pdf
PWC	https://paperswithcode.com/paper/auto-completion-for-data-cells-in-relational
Repo	https://github.com/iai-group/cikm2019-table
Framework	none

Speed-up and multi-view extensions to Subclass Discriminant Analysis


Title	Speed-up and multi-view extensions to Subclass Discriminant Analysis
Authors	Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
Abstract	In this paper, we propose a speed-up approach for subclass discriminant analysis and formulate a novel efficient multi-view solution to it. The speed-up approach is developed based on graph embedding and spectral regression approaches that involve eigendecomposition of the corresponding Laplacian matrix and regression to its eigenvectors. We show that by exploiting the structure of the between-class Laplacian matrix, the eigendecomposition step can be substituted with a much faster process. Furthermore, we formulate a novel criterion for multi-view subclass discriminant analysis and show that an efficient solution for it can be obtained in a similar to the single-view manner. We evaluate the proposed methods on nine single-view and nine multi-view datasets and compare them with related existing approaches. Experimental results show that the proposed solutions achieve competitive performance, often outperforming the existing methods. At the same time, they significantly decrease the training time.
Tasks	Graph Embedding
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00794v1
PDF	https://arxiv.org/pdf/1905.00794v1.pdf
PWC	https://paperswithcode.com/paper/speed-up-and-multi-view-extensions-to
Repo	https://github.com/katerynaCh/fastSDA
Framework	none

Probabilistic Models with Deep Neural Networks


Title	Probabilistic Models with Deep Neural Networks
Authors	Andrés R. Masegosa, Rafael Cabañas, Helge Langseth, Thomas D. Nielsen, Antonio Salmerón
Abstract	Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to (i) very restricted model classes where exact or approximate probabilistic inference were feasible, and (ii) small or medium-sized data sets which fit within the main memory of the computer. However, developments in variational inference, a general form of approximate probabilistic inference originated in statistical physics, are allowing probabilistic modeling to overcome these restrictions: (i) Approximate probabilistic inference is now possible over a broad class of probabilistic models containing a large number of parameters, and (ii) scalable inference methods based on stochastic gradient descent and distributed computation engines allow to apply probabilistic modeling over massive data sets. One important practical consequence of these advances is the possibility to include deep neural networks within a probabilistic model to capture complex non-linear stochastic relationships between random variables. These advances in conjunction with the release of novel probabilistic modeling toolboxes have greatly expanded the scope of application of probabilistic models, and allow these models to take advantage of the recent strides made by the deep learning community. In this paper we review the main concepts, methods and tools needed to use deep neural networks within a probabilistic modeling framework.
Tasks
Published	2019-08-09
URL	https://arxiv.org/abs/1908.03442v3
PDF	https://arxiv.org/pdf/1908.03442v3.pdf
PWC	https://paperswithcode.com/paper/probabilistic-models-with-deep-neural
Repo	https://github.com/PGM-Lab/ProbModelsDNNs
Framework	tf