Paper Group ANR 1167
Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications. Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography. Deep Kernel Learning for Clustering. Multi-Model Investigative Exploration of Social Media Data with boutique: A Case Study in Public Health. All-Action Policy Gradient M …
Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications
| Title | Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications |
| Authors | Andreas Venzke, Spyros Chatzivasileiadis |
| Abstract | This paper presents for the first time, to our knowledge, a framework for verifying neural network behavior in power system applications. Up to this moment, neural networks have been applied in power systems as a black-box; this has presented a major barrier for their adoption in practice. Developing a rigorous framework based on mixed integer linear programming, our methods can determine the range of inputs that neural networks classify as safe or unsafe, and are able to systematically identify adversarial examples. Such methods have the potential to build the missing trust of power system operators on neural networks, and unlock a series of new applications in power systems. This paper presents the framework, methods to assess and improve neural network robustness in power systems, and addresses concerns related to scalability and accuracy. We demonstrate our methods on the IEEE 9-bus, 14-bus, and 162-bus systems, treating both N-1 security and small-signal stability. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01624v2 |
| https://arxiv.org/pdf/1910.01624v2.pdf | |
| PWC | https://paperswithcode.com/paper/verification-of-neural-network-behaviour |
| Repo | |
| Framework | |
Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography
| Title | Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography |
| Authors | Jelmer M. Wolterink, Tim Leiner, Ivana Išgum |
| Abstract | Detection of coronary artery stenosis in coronary CT angiography (CCTA) requires highly personalized surface meshes enclosing the coronary lumen. In this work, we propose to use graph convolutional networks (GCNs) to predict the spatial location of vertices in a tubular surface mesh that segments the coronary artery lumen. Predictions for individual vertex locations are based on local image features as well as on features of neighboring vertices in the mesh graph. The method was trained and evaluated using the publicly available Coronary Artery Stenoses Detection and Quantification Evaluation Framework. Surface meshes enclosing the full coronary artery tree were automatically extracted. A quantitative evaluation on 78 coronary artery segments showed that these meshes corresponded closely to reference annotations, with a Dice similarity coefficient of 0.75/0.73, a mean surface distance of 0.25/0.28 mm, and a Hausdorff distance of 1.53/1.86 mm in healthy/diseased vessel segments. The results showed that inclusion of mesh information in a GCN improves segmentation overlap and accuracy over a baseline model without interaction on the mesh. The results indicate that GCNs allow efficient extraction of coronary artery surface meshes and that the use of GCNs leads to regular and more accurate meshes. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05343v1 |
| https://arxiv.org/pdf/1908.05343v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-networks-for-coronary |
| Repo | |
| Framework | |
Deep Kernel Learning for Clustering
| Title | Deep Kernel Learning for Clustering |
| Authors | Chieh Wu, Zulqarnain Khan, Yale Chang, Stratis Ioannidis, Jennifer Dy |
| Abstract | We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data. Our neural network produces sample embeddings that are motivated by–and are at least as expressive as–spectral clustering. Our training objective, based on the Hilbert Schmidt Information Criterion, can be optimized via gradient adaptations on the Stiefel manifold, leading to significant acceleration over spectral methods relying on eigendecompositions. Finally, our trained embedding can be directly applied to out-of-sample data. We show experimentally that our approach outperforms several state-of-the-art deep clustering methods, as well as traditional approaches such as $k$-means and spectral clustering over a broad array of real-life and synthetic datasets. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03515v3 |
| https://arxiv.org/pdf/1908.03515v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-kernel-learning-for-clustering |
| Repo | |
| Framework | |
Multi-Model Investigative Exploration of Social Media Data with boutique: A Case Study in Public Health
| Title | Multi-Model Investigative Exploration of Social Media Data with boutique: A Case Study in Public Health |
| Authors | Junan Guo, Subhasis Dasgupta, Amarnath Gupta |
| Abstract | We present our experience with a data science problem in Public Health, where researchers use social media (Twitter) to determine whether the public shows awareness of HIV prevention measures offered by Public Health campaigns. To help the researcher, we develop an investigative exploration system called boutique that allows a user to perform a multi-step visualization and exploration of data through a dashboard interface. Unique features of boutique includes its ability to handle heterogeneous types of data provided by a polystore, and its ability to use computation as part of the investigative exploration process. In this paper, we present the design of the boutique middleware and walk through an investigation process for a real-life problem. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10482v1 |
| https://arxiv.org/pdf/1905.10482v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-model-investigative-exploration-of |
| Repo | |
| Framework | |
All-Action Policy Gradient Methods: A Numerical Integration Approach
| Title | All-Action Policy Gradient Methods: A Numerical Integration Approach |
| Authors | Benjamin Petit, Loren Amdahl-Culleton, Yao Liu, Jimmy Smith, Pierre-Luc Bacon |
| Abstract | While often stated as an instance of the likelihood ratio trick [Rubinstein, 1989], the original policy gradient theorem [Sutton, 1999] involves an integral over the action space. When this integral can be computed, the resulting “all-action” estimator [Sutton, 2001] provides a conditioning effect [Bratley, 1987] reducing the variance significantly compared to the REINFORCE estimator [Williams, 1992]. In this paper, we adopt a numerical integration perspective to broaden the applicability of the all-action estimator to general spaces and to any function class for the policy or critic components, beyond the Gaussian case considered by [Ciosek, 2018]. In addition, we provide a new theoretical result on the effect of using a biased critic which offers more guidance than the previous “compatible features” condition of [Sutton, 1999]. We demonstrate the benefit of our approach in continuous control tasks with nonlinear function approximation. Our results show improved performance and sample efficiency. |
| Tasks | Continuous Control, Policy Gradient Methods |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09093v1 |
| https://arxiv.org/pdf/1910.09093v1.pdf | |
| PWC | https://paperswithcode.com/paper/all-action-policy-gradient-methods-a |
| Repo | |
| Framework | |
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning
| Title | Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning |
| Authors | Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh |
| Abstract | Multi-step greedy policies have been extensively used in model-based Reinforcement Learning (RL) and in the case when a model of the environment is available (e.g., in the game of Go). In this work, we explore the benefits of multi-step greedy policies in model-free RL when employed in the framework of multi-step Dynamic Programming (DP): multi-step Policy and Value Iteration. These algorithms iteratively solve short-horizon decision problems and converge to the optimal solution of the original one. By using model-free algorithms as solvers of the short-horizon problems we derive fully model-free algorithms which are instances of the multi-step DP framework. As model-free algorithms are prone to instabilities w.r.t. the decision problem horizon, this simple approach can help in mitigating these instabilities and results in an improved model-free algorithms. We test this approach and show results on both discrete and continuous control problems. |
| Tasks | Continuous Control, Game of Go |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02919v2 |
| https://arxiv.org/pdf/1910.02919v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-step-greedy-policies-in-model-free-deep-1 |
| Repo | |
| Framework | |
Towards Autoencoding Variational Inference for Aspect-based Opinion Summary
| Title | Towards Autoencoding Variational Inference for Aspect-based Opinion Summary |
| Authors | Tai Hoang, Huy Le, Tho Quan |
| Abstract | Aspect-based Opinion Summary (AOS), consisting of aspect discovery and sentiment classification steps, has recently been emerging as one of the most crucial data mining tasks in e-commerce systems. Along this direction, the LDA-based model is considered as a notably suitable approach, since this model offers both topic modeling and sentiment classification. However, unlike traditional topic modeling, in the context of aspect discovery it is often required some initial seed words, whose prior knowledge is not easy to be incorporated into LDA models. Moreover, LDA approaches rely on sampling methods, which need to load the whole corpus into memory, making them hardly scalable. In this research, we study an alternative approach for AOS problem, based on Autoencoding Variational Inference (AVI). Firstly, we introduce the Autoencoding Variational Inference for Aspect Discovery (AVIAD) model, which extends the previous work of Autoencoding Variational Inference for Topic Models (AVITM) to embed prior knowledge of seed words. This work includes enhancement of the previous AVI architecture and also modification of the loss function. Ultimately, we present the Autoencoding Variational Inference for Joint Sentiment/Topic (AVIJST) model. In this model, we substantially extend the AVI model to support the JST model, which performs topic modeling for corresponding sentiment. The experimental results show that our proposed models enjoy higher topic coherent, faster convergence time and better accuracy on sentiment classification, as compared to their LDA-based counterparts. |
| Tasks | Sentiment Analysis, Topic Models |
| Published | 2019-02-07 |
| URL | https://arxiv.org/abs/1902.02507v3 |
| https://arxiv.org/pdf/1902.02507v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-autoencoding-variational-inference |
| Repo | |
| Framework | |
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
| Title | Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling |
| Authors | Che Wang, Yanqiu Wu, Quan Vuong, Keith Ross |
| Abstract | We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entropy term in SAC addresses action saturation due to the bounded nature of the action spaces. With this insight, we propose a streamlined algorithm with a simple normalization scheme or with inverted gradients. We show that both approaches can match SAC’s sample efficiency performance without the need of entropy maximization. We then propose a simple non-uniform sampling method for selecting transitions from the replay buffer during training. Extensive experimental results demonstrate that our proposed sampling scheme leads to state of the art sample efficiency on challenging continuous control tasks. We combine all of our findings into one simple algorithm, which we call Streamlined Off Policy with Emphasizing Recent Experience, for which we provide robust public-domain code. |
| Tasks | Continuous Control |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02208v3 |
| https://arxiv.org/pdf/1910.02208v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-simplicity-in-deep-reinforcement-1 |
| Repo | |
| Framework | |
Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurization
| Title | Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurization |
| Authors | Evan N. Feinberg, Robert Sheridan, Elizabeth Joshi, Vijay S. Pande, Alan C. Cheng |
| Abstract | The Absorption, Distribution, Metabolism, Elimination, and Toxicity (ADMET) properties of drug candidates are estimated to account for up to 50% of all clinical trial failures. Predicting ADMET properties has therefore been of great interest to the cheminformatics and medicinal chemistry communities in recent decades. Traditional cheminformatics approaches, whether the learner is a random forest or a deep neural network, leverage fixed fingerprint feature representations of molecules. In contrast, in this paper, we learn the features most relevant to each chemical task at hand by representing each molecule explicitly as a graph, where each node is an atom and each edge is a bond. By applying graph convolutions to this explicit molecular representation, we achieve, to our knowledge, unprecedented accuracy in prediction of ADMET properties. By challenging our methodology with rigorous cross-validation procedures and prospective analyses, we show that deep featurization better enables molecular predictors to not only interpolate but also extrapolate to new regions of chemical space. |
| Tasks | |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.11789v1 |
| http://arxiv.org/pdf/1903.11789v1.pdf | |
| PWC | https://paperswithcode.com/paper/step-change-improvement-in-admet-prediction |
| Repo | |
| Framework | |
Evaluation of Machine Learning-based Anomaly Detection Algorithms on an Industrial Modbus/TCP Data Set
| Title | Evaluation of Machine Learning-based Anomaly Detection Algorithms on an Industrial Modbus/TCP Data Set |
| Authors | Simon Duque Anton, Suneetha Kanoor, Daniel Fraunholz, Hans Dieter Schotten |
| Abstract | In the context of the Industrial Internet of Things, communication technology, originally used in home and office environments, is introduced into industrial applications. Commercial off-the-shelf products, as well as unified and well-established communication protocols make this technology easy to integrate and use. Furthermore, productivity is increased in comparison to classic industrial control by making systems easier to manage, set up and configure. Unfortunately, most attack surfaces of home and office environments are introduced into industrial applications as well, which usually have very few security mechanisms in place. Over the last years, several technologies tackling that issue have been researched. In this work, machine learning-based anomaly detection algorithms are employed to find malicious traffic in a synthetically generated data set of Modbus/TCP communication of a fictitious industrial scenario. The applied algorithms are Support Vector Machine (SVM), Random Forest, k-nearest neighbour and k-means clustering. Due to the synthetic data set, supervised learning is possible. Support Vector Machine and k-nearest neighbour perform well with different data sets, while k-nearest neighbour and k-means clustering do not perform satisfactorily. |
| Tasks | Anomaly Detection |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11757v1 |
| https://arxiv.org/pdf/1905.11757v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-machine-learning-based-anomaly |
| Repo | |
| Framework | |
Fault Diagnosis of Rotary Machines using Deep Convolutional Neural Network with three axis signal input
| Title | Fault Diagnosis of Rotary Machines using Deep Convolutional Neural Network with three axis signal input |
| Authors | Davor Kolar, Dragutin Lisjak, Michal Pajak, Danijel Pavkovic |
| Abstract | Recent trends focusing on Industry 4.0 concept and smart manufacturing arise a data-driven fault diagnosis as key topic in condition-based maintenance. Fault diagnosis is considered as an essential task in rotary machinery since possibility of an early detection and diagnosis of the faulty condition can save both time and money. Traditional data-driven techniques of fault diagnosis require signal processing for feature extraction, as they are unable to work with raw signal data, consequently leading to need for expert knowledge and human work. The emergence of deep learning architectures in condition-based maintenance promises to ensure high performance fault diagnosis while lowering necessity for expert knowledge and human work. This paper presents developed technique for deep learning-based data-driven fault diagnosis of rotary machinery. The proposed technique input raw three axis accelerometer signal as high-definition image into deep learning layers which automatically extract signal features, enabling high classification accuracy. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02444v2 |
| https://arxiv.org/pdf/1906.02444v2.pdf | |
| PWC | https://paperswithcode.com/paper/fault-diagnosis-of-rotary-machines-using-deep |
| Repo | |
| Framework | |
The Differentiable Cross-Entropy Method
| Title | The Differentiable Cross-Entropy Method |
| Authors | Brandon Amos, Denis Yarats |
| Abstract | We study the Cross-Entropy Method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant (DCEM) that enables us to differentiate the output of CEM with respect to the objective function’s parameters. In the machine learning setting this brings CEM inside of the end-to-end learning pipeline where this has otherwise been impossible. We show applications in a synthetic energy-based structured prediction task and in non-convex continuous control. In the control setting we show on the simulated cheetah and walker tasks that we can embed their optimal action sequences with DCEM and then use policy optimization to fine-tune components of the controller as a step towards combining model-based and model-free RL. |
| Tasks | Continuous Control, Structured Prediction |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12830v1 |
| https://arxiv.org/pdf/1909.12830v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-differentiable-cross-entropy-method-1 |
| Repo | |
| Framework | |
MERL: Multi-Head Reinforcement Learning
| Title | MERL: Multi-Head Reinforcement Learning |
| Authors | Yannis Flet-Berliac, Philippe Preux |
| Abstract | A common challenge in reinforcement learning is how to convert the agent’s interactions with an environment into fast and robust learning. For instance, earlier work makes use of domain knowledge to improve existing reinforcement learning algorithms in complex tasks. While promising, previously acquired knowledge is often costly and challenging to scale up. Instead, we decide to consider problem knowledge with signals from quantities relevant to solve any task, e.g., self-performance assessment and accurate expectations. $\mathcal{V}^{ex}$ is such a quantity. It is the fraction of variance explained by the value function $V$ and measures the discrepancy between $V$ and the returns. Taking advantage of $\mathcal{V}^{ex}$, we propose MERL, a general framework for structuring reinforcement learning by injecting problem knowledge into policy gradient updates. As a result, the agent is not only optimized for a reward but learns using problem-focused quantities provided by MERL, applicable out-of-the-box to any task. In this paper: (a) We introduce and define MERL, the multi-head reinforcement learning framework we use throughout this work. (b) We conduct experiments across a variety of standard benchmark environments, including 9 continuous control tasks, where results show improved performance. (c) We demonstrate that MERL also improves transfer learning on a set of challenging pixel-based tasks. (d) We ponder how MERL tackles the problem of reward sparsity and better conditions the feature space of reinforcement learning agents. |
| Tasks | Continuous Control, Transfer Learning |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11939v6 |
| https://arxiv.org/pdf/1909.11939v6.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-control-using-generalized |
| Repo | |
| Framework | |
RGB-T Image Saliency Detection via Collaborative Graph Learning
| Title | RGB-T Image Saliency Detection via Collaborative Graph Learning |
| Authors | Zhengzheng Tu, Tian Xia, Chenglong Li, Xiaoxiao Wang, Yan Ma, Jin Tang |
| Abstract | Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods. |
| Tasks | Saliency Detection |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06741v1 |
| https://arxiv.org/pdf/1905.06741v1.pdf | |
| PWC | https://paperswithcode.com/paper/rgb-t-image-saliency-detection-via |
| Repo | |
| Framework | |
On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning
| Title | On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning |
| Authors | Tao Li, Quanyan Zhu |
| Abstract | In this paper, we propose a generic framework for devising an adaptive approximation scheme for value function approximation in reinforcement learning, which introduces multiscale approximation. The two basic ingredients are multiresolution analysis as well as tree approximation. Starting from simple refinable functions, multiresolution analysis enables us to construct a wavelet system from which the basis functions are selected adaptively, resulting in a tree structure. Furthermore, we present the convergence rate of our multiscale approximation which does not depend on the regularity of basis functions. |
| Tasks | |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08578v1 |
| https://arxiv.org/pdf/1908.08578v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-convergence-rate-of-adaptive-multiscale |
| Repo | |
| Framework | |
