Paper Group ANR 427
ODE-based Deep Network for MRI Reconstruction. SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions. Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning. Deep Adversarial Network Alignment. Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation. Normalizin …
ODE-based Deep Network for MRI Reconstruction
| Title | ODE-based Deep Network for MRI Reconstruction |
| Authors | Ali Pour Yazdanpanah, Onur Afacan, Simon K. Warfield |
| Abstract | Fast data acquisition in Magnetic Resonance Imaging (MRI) is vastly in demand and scan time directly depends on the number of acquired k-space samples. The data-driven methods based on deep neural networks have resulted in promising improvements, compared to the conventional methods, in image reconstruction algorithms. The connection between deep neural network and Ordinary Differential Equation (ODE) has been observed and studied recently. The studies show that different residual networks can be interpreted as Euler discretization of an ODE. In this paper, we propose an ODE-based deep network for MRI reconstruction to enable the rapid acquisition of MR images with improved image quality. Our results with undersampled data demonstrate that our method can deliver higher quality images in comparison to the reconstruction methods based on the standard UNet network and Residual network. |
| Tasks | Image Reconstruction |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12325v1 |
| https://arxiv.org/pdf/1912.12325v1.pdf | |
| PWC | https://paperswithcode.com/paper/ode-based-deep-network-for-mri-reconstruction |
| Repo | |
| Framework | |
SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
| Title | SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions |
| Authors | A. Ali Heydari, Craig A. Thompson, Asif Mehmood |
| Abstract | Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning. However, existing frameworks of adaptive loss functions often suffer from slow convergence and poor choice of weights for the loss components. Traditionally, the elements of a multi-part loss function are weighted equally or their weights are determined through heuristic approaches that yield near-optimal (or sub-optimal) results. To address this problem, we propose a family of methods, called SoftAdapt, that dynamically change function weights for multi-part loss functions based on live performance statistics of the component losses. SoftAdapt is mathematically intuitive, computationally efficient and straightforward to implement. In this paper, we present the mathematical formulation and pseudocode for SoftAdapt, along with results from applying our methods to image reconstruction (Sparse Autoencoders) and synthetic data generation (Introspective Variational Autoencoders). |
| Tasks | Image Reconstruction, Synthetic Data Generation |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12355v1 |
| https://arxiv.org/pdf/1912.12355v1.pdf | |
| PWC | https://paperswithcode.com/paper/softadapt-techniques-for-adaptive-loss |
| Repo | |
| Framework | |
Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning
| Title | Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning |
| Authors | Andreas Sedlmeier, Thomas Gabor, Thomy Phan, Lenz Belzner, Claudia Linnhoff-Popien |
| Abstract | Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent’s epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. We further present a first viable solution for calculating a dynamic classification threshold, based on the uncertainty distribution of the training data. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to reliably detect OOD situations. In summary, UBOOD presents a viable approach for OOD classification in deep RL settings by leveraging the epistemic uncertainty of the agent’s value function. |
| Tasks | Bayesian Inference |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00496v1 |
| https://arxiv.org/pdf/2001.00496v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-based-out-of-distribution-1 |
| Repo | |
| Framework | |
Deep Adversarial Network Alignment
| Title | Deep Adversarial Network Alignment |
| Authors | Tyler Derr, Hamid Karimi, Xiaorui Liu, Jiejun Xu, Jiliang Tang |
| Abstract | Network alignment, in general, seeks to discover the hidden underlying correspondence between nodes across two (or more) networks when given their network structure. However, most existing network alignment methods have added assumptions of additional constraints to guide the alignment, such as having a set of seed node-node correspondences across the networks or the existence of side-information. Instead, we seek to develop a general network alignment algorithm that makes no additional assumptions. Recently, network embedding has proven effective in many network analysis tasks, but embeddings of different networks are not aligned. Thus, we present our Deep Adversarial Network Alignment (DANA) framework that first uses deep adversarial learning to discover complex mappings for aligning the embedding distributions of the two networks. Then, using our learned mapping functions, DANA performs an efficient nearest neighbor node alignment. We perform experiments on real world datasets to show the effectiveness of our framework for first aligning the graph embedding distributions and then discovering node alignments that outperform existing methods. |
| Tasks | Graph Embedding, Network Embedding |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10307v1 |
| http://arxiv.org/pdf/1902.10307v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-adversarial-network-alignment |
| Repo | |
| Framework | |
Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation
| Title | Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation |
| Authors | Jinwei Xing, Xinyun Zou, Jeffrey L. Krichmar |
| Abstract | Robots and self-driving vehicles face a number of challenges when navigating through real environments. Successful navigation in dynamic environments requires prioritizing subtasks and monitoring resources. Animals are under similar constraints. It has been shown that the neuromodulator serotonin regulates impulsiveness and patience in animals. In the present paper, we take inspiration from the serotonergic system and apply it to the task of robot navigation. In a set of outdoor experiments, we show how changing the level of patience can affect the amount of time the robot will spend searching for a desired location. To navigate GPS compromised environments, we introduce a deep reinforcement learning paradigm in which the robot learns to follow sidewalks. This may further regulate a tradeoff between a smooth long route and a rough shorter route. Using patience as a parameter may be beneficial for autonomous systems under time pressure. |
| Tasks | Robot Navigation |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06533v1 |
| https://arxiv.org/pdf/1909.06533v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuromodulated-patience-for-robot-and-self |
| Repo | |
| Framework | |
Normalizing flows for deep anomaly detection
| Title | Normalizing flows for deep anomaly detection |
| Authors | Artem Ryzhikov, Maxim Borisyak, Andrey Ustyuzhanin, Denis Derkach |
| Abstract | Anomaly detection for complex data is a challenging task from the perspective of machine learning. In this work, weconsider cases with missing certain kinds of anomalies in the training dataset, while significant statistics for the normal class isavailable. For such scenarios, conventional supervised methods might suffer from the class imbalance, while unsupervised methodstend to ignore difficult anomalous examples. We extend the idea of the supervised classification approach for class-imbalanceddatasets by exploiting normalizing flows for proper Bayesian inference of the posterior probabilities. |
| Tasks | Anomaly Detection, Bayesian Inference |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09323v1 |
| https://arxiv.org/pdf/1912.09323v1.pdf | |
| PWC | https://paperswithcode.com/paper/normalizing-flows-for-deep-anomaly-detection |
| Repo | |
| Framework | |
Keyword Aware Influential Community Search in Large Attributed Graphs
| Title | Keyword Aware Influential Community Search in Large Attributed Graphs |
| Authors | Md. Saiful Islam, Mohammed Eunus Ali, Yong-Bin Kang, Timos Sellis, Farhana M. Choudhury |
| Abstract | We introduce a novel keyword-aware influential community query KICQ that finds the most influential communities from an attributed graph, where an influential community is defined as a closely connected group of vertices having some dominance over other groups of vertices with the expertise (a set of keywords) matching with the query terms (words or phrases). We first design the KICQ that facilitates users to issue an influential CS query intuitively by using a set of query terms, and predicates (AND or OR). In this context, we propose a novel word-embedding based similarity model that enables semantic community search, which substantially alleviates the limitations of exact keyword based community search. Next, we propose a new influence measure for a community that considers both the cohesiveness and influence of the community and eliminates the need for specifying values of internal parameters of a network. Finally, we propose two efficient algorithms for searching influential communities in large attributed graphs. We present detailed experiments and a case study to demonstrate the effectiveness and efficiency of the proposed approaches. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02114v1 |
| https://arxiv.org/pdf/1912.02114v1.pdf | |
| PWC | https://paperswithcode.com/paper/keyword-aware-influential-community-search-in |
| Repo | |
| Framework | |
Multimodal Deep Models for Predicting Affective Responses Evoked by Movies
| Title | Multimodal Deep Models for Predicting Affective Responses Evoked by Movies |
| Authors | Ha Thi Phuong Thao, Dorien Herremans, Gemma Roig |
| Abstract | The goal of this study is to develop and analyze multimodal models for predicting experienced affective responses of viewers watching movie clips. We develop hybrid multimodal prediction models based on both the video and audio of the clips. For the video content, we hypothesize that both image content and motion are crucial features for evoked emotion prediction. To capture such information, we extract features from RGB frames and optical flow using pre-trained neural networks. For the audio model, we compute an enhanced set of low-level descriptors including intensity, loudness, cepstrum, linear predictor coefficients, pitch and voice quality. Both visual and audio features are then concatenated to create audio-visual features, which are used to predict the evoked emotion. To classify the movie clips into the corresponding affective response categories, we propose two approaches based on deep neural network models. The first one is based on fully connected layers without memory on the time component, the second incorporates the sequential dependency with a long short-term memory recurrent neural network (LSTM). We perform a thorough analysis of the importance of each feature set. Our experiments reveal that in our set-up, predicting emotions at each time step independently gives slightly better accuracy performance than with the LSTM. Interestingly, we also observe that the optical flow is more informative than the RGB in videos, and overall, models using audio features are more accurate than those based on video features when making the final prediction of evoked emotions. |
| Tasks | Optical Flow Estimation |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06957v2 |
| https://arxiv.org/pdf/1909.06957v2.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-deep-models-for-predicting |
| Repo | |
| Framework | |
Defining Quantum Neural Networks via Quantum Time Evolution
| Title | Defining Quantum Neural Networks via Quantum Time Evolution |
| Authors | Aditya Dendukuri, Blake Keeling, Arash Fereidouni, Joshua Burbridge, Khoa Luu, Hugh Churchill |
| Abstract | This work presents a novel fundamental algorithm for for defining and training Neural Networks in Quantum Information based on time evolution and the Hamiltonian. Classical Neural Network algorithms (ANN) are computationally expensive. For example, in image classification, representing an image pixel by pixel using classical information requires an enormous amount of computational memory resources. Hence, exploring methods to represent images in a different paradigm of information is important. Quantum Neural Networks (QNNs) have been explored for over 20 years. The current forefront work based on Variational Quantum Circuits is specifically defined for the Continuous Variable (CV) Model of quantum computers. In this work, a model is proposed which is defined at a more fundamental level and hence can be inherited by any variants of quantum computing models. This work also presents a quantum backpropagation algorithm to train our QNN model and validate this algorithm on the MNIST dataset on a quantum computer simulation. |
| Tasks | Image Classification |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10912v2 |
| https://arxiv.org/pdf/1905.10912v2.pdf | |
| PWC | https://paperswithcode.com/paper/defining-quantum-neural-networks-via-quantum |
| Repo | |
| Framework | |
Information matrices and generalization
| Title | Information matrices and generalization |
| Authors | Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Mangazol, Yoshua Bengio, Nicolas Le Roux |
| Abstract | This work revisits the use of information criteria to characterize the generalization of deep learning models. In particular, we empirically demonstrate the effectiveness of the Takeuchi information criterion (TIC), an extension of the Akaike information criterion (AIC) for misspecified models, in estimating the generalization gap, shedding light on why quantities such as the number of parameters cannot quantify generalization. The TIC depends on both the Hessian of the loss H and the covariance of the gradients C. By exploring the similarities and differences between these two matrices as well as the Fisher information matrix F, we study the interplay between noise and curvature in deep models. We also address the question of whether C is a reasonable approximation to F, as is commonly assumed. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07774v1 |
| https://arxiv.org/pdf/1906.07774v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-matrices-and-generalization |
| Repo | |
| Framework | |
Charged particle tracking with quantum annealing-inspired optimization
| Title | Charged particle tracking with quantum annealing-inspired optimization |
| Authors | Alexander Zlokapa, Abhishek Anand, Jean-Roch Vlimant, Javier M. Duarte, Joshua Job, Daniel Lidar, Maria Spiropulu |
| Abstract | At the High Luminosity Large Hadron Collider (HL-LHC), traditional track reconstruction techniques that are critical for analysis are expected to face challenges due to scaling with track density. Quantum annealing has shown promise in its ability to solve combinatorial optimization problems amidst an ongoing effort to establish evidence of a quantum speedup. As a step towards exploiting such potential speedup, we investigate a track reconstruction approach by adapting the existing geometric Denby-Peterson (Hopfield) network method to the quantum annealing framework and to HL-LHC conditions. Furthermore, we develop additional techniques to embed the problem onto existing and near-term quantum annealing hardware. Results using simulated annealing and quantum annealing with the D-Wave 2X system on the TrackML dataset are presented, demonstrating the successful application of a quantum annealing-inspired algorithm to the track reconstruction challenge. We find that combinatorial optimization problems can effectively reconstruct tracks, suggesting possible applications for fast hardware-specific implementations at the LHC while leaving open the possibility of a quantum speedup for tracking. |
| Tasks | Combinatorial Optimization |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04475v1 |
| https://arxiv.org/pdf/1908.04475v1.pdf | |
| PWC | https://paperswithcode.com/paper/charged-particle-tracking-with-quantum |
| Repo | |
| Framework | |
Segmentation of points of interest during fetal cardiac assesment in the first trimester from color Doppler ultrasound
| Title | Segmentation of points of interest during fetal cardiac assesment in the first trimester from color Doppler ultrasound |
| Authors | Ruxandra Stoean, Dominic Iliescu, Catalin Stoean |
| Abstract | The present paper puts forward an incipient study that uses a traditional segmentation method based on Zernike moments for extracting significant features from frames of fetal echocardiograms from first trimester color Doppler examinations. A distance based approach is then used on the obtained indicators to classify frames of three given categories that should be present in a normal heart condition. The computational tool shows promise in supporting the obstetrician in a rapid recognition of heart views during screening. |
| Tasks | |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11903v1 |
| https://arxiv.org/pdf/1909.11903v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-points-of-interest-during |
| Repo | |
| Framework | |
Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location
| Title | Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location |
| Authors | Andrea Lodi, Luca Mossina, Emmanuel Rachelson |
| Abstract | We present an approach to couple the resolution of Combinatorial Optimization problems with methods from Machine Learning, applied to the single source, capacitated, facility location problem. Our study is framed in the context where a reference facility location optimization problem is given. Assuming there exist data for many variations of the reference problem (historical or simulated) along with their optimal solution, we study how one can exploit these to make predictions about an unseen new instance. We demonstrate how a classifier can be built from these data to determine whether the solution to the reference problem still applies to a new instance. In case the reference solution is partially applicable, we build a regressor indicating the magnitude of the expected change, and conversely how much of it can be kept for the new instance. This insight, derived from a priori information, is expressed via an additional constraint in the original mathematical programming formulation. We present an empirical evaluation and discuss the benefits, drawbacks and perspectives of such an approach. Although presented through the application to the facility location problem, the approach developed here is general and explores a new perspective on the exploitation of past experience in combinatorial optimization. |
| Tasks | Combinatorial Optimization |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05765v1 |
| https://arxiv.org/pdf/1907.05765v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-handle-parameter-perturbations-in |
| Repo | |
| Framework | |
Highly parallel algorithm for the Ising ground state searching problem
| Title | Highly parallel algorithm for the Ising ground state searching problem |
| Authors | A. Yavorsky, L. A. Markovich, E. A. Polyakov, A. N. Rubtsov |
| Abstract | Finding an energy minimum in the Ising model is an exemplar objective, associated with many combinatorial optimization problems, that is computationally hard in general, but occurs in all areas of modern science. There are several numerical methods, providing solution for the medium size Ising spin systems. However, they are either computationally slow and badly parallelized, or do not give sufficiently good results for the large systems. In this paper, we present a highly parallel algorithm, called Mean-field Annealing from a Random State (MARS), incorporating the best features of the classical simulated annealing (SA) and Mean-Field Annealing (MFA) methods. The algorithm is based on the mean-field descent from a randomly selected configuration and temperature. Since a single run requires little computational effort, the effectiveness can be achieved by massive parallelisation. MARS shows excellent performance both on the large Ising spin systems and on the set of exemplary maximum cut benchmark instances in terms of both solution quality and computational time. |
| Tasks | Combinatorial Optimization |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05124v2 |
| https://arxiv.org/pdf/1907.05124v2.pdf | |
| PWC | https://paperswithcode.com/paper/highly-parallel-algorithm-for-the-ising |
| Repo | |
| Framework | |
Predicting Auction Price of Vehicle License Plate with Deep Residual Learning
| Title | Predicting Auction Price of Vehicle License Plate with Deep Residual Learning |
| Authors | Vinci Chow |
| Abstract | Due to superstition, license plates with desirable combinations of characters are highly sought after in China, fetching prices that can reach into the millions in government-held auctions. Despite the high stakes involved, there has been essentially no attempt to provide price estimates for license plates. We present an end-to-end neural network model that simultaneously predict the auction price, gives the distribution of prices and produces latent feature vectors. While both types of neural network architectures we consider outperform simpler machine learning methods, convolutional networks outperform recurrent networks for comparable training time or model complexity. The resulting model powers our online price estimator and search engine. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.04879v1 |
| https://arxiv.org/pdf/1910.04879v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-auction-price-of-vehicle-license-2 |
| Repo | |
| Framework | |
