January 25, 2020

3153 words 15 mins read

Paper Group ANR 1728

Convolutional Restricted Boltzmann Machine Based-Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer. Transferability and Hardness of Supervised Classification Tasks. Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces. Speeding up reinforcement learnin …

Convolutional Restricted Boltzmann Machine Based-Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer


Title	Convolutional Restricted Boltzmann Machine Based-Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
Authors	Li Wang, Lihui Wang, Qijian Chen, Caixia Sun, Xinyu Cheng, Yuemin Zhu
Abstract	We proposed a novel convolutional restricted Boltzmann machine CRBM-based radiomic method for predicting pathologic complete response (pCR) to neoadjuvant chemotherapy treatment (NACT) in breast cancer. The method consists of extracting semantic features from CRBM network, and pCR prediction. It was evaluated on the dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data of 57 patients and using the area under the receiver operating characteristic curve (AUC). Traditional radiomics features and the semantic features learned from CRBM network were extracted from the images acquired before and after the administration of NACT. After the feature selection, the support vector machine (SVM), logistic regression (LR) and random forest (RF) were trained to predict the pCR status. Compared to traditional radiomic methods, the proposed CRBM-based radiomic method yielded an AUC of 0.92 for the prediction with the images acquired before and after NACT, and an AUC of 0.87 for the pretreatment prediction, which was increased by about 38%. The results showed that the CRBM-based radiomic method provided a potential means for accurately predicting the pCR to NACT in breast cancer before the treatment, which is very useful for making more appropriate and personalized treatment regimens.
Tasks	Feature Selection
Published	2019-05-23
URL	https://arxiv.org/abs/1905.13312v1
PDF	https://arxiv.org/pdf/1905.13312v1.pdf
PWC	https://paperswithcode.com/paper/190513312
Repo
Framework

Transferability and Hardness of Supervised Classification Tasks


Title	Transferability and Hardness of Supervised Classification Tasks
Authors	Anh T. Tran, Cuong V. Nguyen, Tal Hassner
Abstract	We propose a novel approach for estimating the difficulty and transferability of supervised classification tasks. Unlike previous work, our approach is solution agnostic and does not require or assume trained models. Instead, we estimate these values using an information theoretic approach: treating training labels as random variables and exploring their statistics. When transferring from a source to a target task, we consider the conditional entropy between two such variables (i.e., label assignments of the two tasks). We show analytically and empirically that this value is related to the loss of the transferred model. We further show how to use this value to estimate task hardness. We test our claims extensively on three large scale data sets – CelebA (40 tasks), Animals with Attributes 2 (85 tasks), and Caltech-UCSD Birds 200 (312 tasks) – together representing 437 classification tasks. We provide results showing that our hardness and transferability estimates are strongly correlated with empirical hardness and transferability. As a case study, we transfer a learned face recognition model to CelebA attribute classification tasks, showing state of the art accuracy for tasks estimated to be highly transferable.
Tasks	Face Recognition
Published	2019-08-21
URL	https://arxiv.org/abs/1908.08142v1
PDF	https://arxiv.org/pdf/1908.08142v1.pdf
PWC	https://paperswithcode.com/paper/transferability-and-hardness-of-supervised
Repo
Framework

Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces


Title	Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
Authors	Chen Tessler, Tom Zahavy, Deborah Cohen, Daniel J. Mankowitz, Shie Mannor
Abstract	We propose a computationally efficient algorithm that combines compressed sensing with imitation learning to solve text-based games with combinatorial action spaces. Specifically, we introduce a new compressed sensing algorithm, named IK-OMP, which can be seen as an extension to the Orthogonal Matching Pursuit (OMP). We incorporate IK-OMP into a supervised imitation learning setting and show that the combined approach (Sparse Imitation Learning, Sparse-IL) solves the entire text-based game of Zork1 with an action space of approximately 10 million actions given both perfect and noisy demonstrations.
Tasks	Decision Making, Imitation Learning, Word Embeddings
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09700v3
PDF	https://arxiv.org/pdf/1905.09700v3.pdf
PWC	https://paperswithcode.com/paper/action-assembly-sparse-imitation-learning-for
Repo
Framework

Speeding up reinforcement learning by combining attention and agency features


Title	Speeding up reinforcement learning by combining attention and agency features
Authors	Berkay Demirel, Martí Sánchez-Fibla
Abstract	When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality. Reinforcement Learning (RL) has been able to deal with big state spaces, including states derived from pixel images in Atari games, but the learning is slow, depends on the brute force mapping from the global state to the action values (Q-function), thus its performance is severely affected by the dimensionality of the state and cannot be transferred to other games or other parts of the same game. We propose different transformations of the input state that combine attention and agency detection mechanisms which both have been addressed separately in RL but not together to our knowledge. We propose and benchmark different architectures including both global and local agency centered versions of the state and also including summaries of the surroundings. Results suggest that even a redundant global-local state network can learn faster than the global alone. Summarized versions of the state look promising to achieve input-size independence learning.
Tasks	Atari Games
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12623v1
PDF	https://arxiv.org/pdf/1912.12623v1.pdf
PWC	https://paperswithcode.com/paper/speeding-up-reinforcement-learning-by
Repo
Framework

Semi-Unsupervised Lifelong Learning for Sentiment Classification: Less Manual Data Annotation and More Self-Studying


Title	Semi-Unsupervised Lifelong Learning for Sentiment Classification: Less Manual Data Annotation and More Self-Studying
Authors	Xianbin Hong, Gautam Pal, Sheng-Uei Guan, Prudence Wong, Dawei Liu, Ka Lok Man, Xin Huang
Abstract	Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Na"ive Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focuses on how to accumulate knowledge during learning and leverage them for further tasks. Meanwhile, the demand for labelled data for training also is significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labelled data and computational cost to achieve the performance as well as or even better than the supervised learning.
Tasks	Sentiment Analysis
Published	2019-04-30
URL	https://arxiv.org/abs/1905.01988v2
PDF	https://arxiv.org/pdf/1905.01988v2.pdf
PWC	https://paperswithcode.com/paper/semi-unsupervised-lifelong-learning-for
Repo
Framework

Adapting Behaviour for Learning Progress


Title	Adapting Behaviour for Learning Progress
Authors	Tom Schaul, Diana Borsa, David Ding, David Szepesvari, Georg Ostrovski, Will Dabney, Simon Osindero
Abstract	Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has not removed the need to tune exploration to the task, because the ideal data for the learning algorithm necessarily depends on its process of learning. We propose to dynamically adapt the data generation by using a non-stationary multi-armed bandit to optimize a proxy of the learning progress. The data distribution is controlled by modulating multiple parameters of the policy (such as stochasticity, consistency or optimism) without significant overhead. The adaptation speed of the bandit can be increased by exploiting the factored modulation structure. We demonstrate on a suite of Atari 2600 games how this unified approach produces results comparable to per-task tuning at a fraction of the cost.
Tasks	Atari Games
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06910v1
PDF	https://arxiv.org/pdf/1912.06910v1.pdf
PWC	https://paperswithcode.com/paper/adapting-behaviour-for-learning-progress-1
Repo
Framework

Deep Bayesian Reward Learning from Preferences


Title	Deep Bayesian Reward Learning from Preferences
Authors	Daniel S. Brown, Scott Niekum
Abstract	Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally intractable for high-dimensional problems because each sample from the posterior requires solving an entire Markov Decision Process (MDP). While there exist non-Bayesian deep IRL methods, these methods typically infer point estimates of reward functions, precluding rigorous safety and uncertainty analysis. We propose Bayesian Reward Extrapolation (B-REX), a highly efficient, preference-based Bayesian reward learning algorithm that scales to high-dimensional, visual control tasks. Our approach uses successor feature representations and preferences over demonstrations to efficiently generate samples from the posterior distribution over the demonstrator’s reward function without requiring an MDP solver. Using samples from the posterior, we demonstrate how to calculate high-confidence bounds on policy performance in the imitation learning setting, in which the ground-truth reward function is unknown. We evaluate our proposed approach on the task of learning to play Atari games via imitation learning from pixel inputs, with no access to the game score. We demonstrate that B-REX learns imitation policies that are competitive with a state-of-the-art deep imitation learning method that only learns a point estimate of the reward function. Furthermore, we demonstrate that samples from the posterior generated via B-REX can be used to compute high-confidence performance bounds for a variety of evaluation policies. We show that high-confidence performance bounds are useful for accurately ranking different evaluation policies when the reward function is unknown. We also demonstrate that high-confidence performance bounds may be useful for detecting reward hacking.
Tasks	Atari Games, Imitation Learning
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04472v1
PDF	https://arxiv.org/pdf/1912.04472v1.pdf
PWC	https://paperswithcode.com/paper/deep-bayesian-reward-learning-from
Repo
Framework

On Neural Architecture Search for Resource-Constrained Hardware Platforms


Title	On Neural Architecture Search for Resource-Constrained Hardware Platforms
Authors	Qing Lu, Weiwen Jiang, Xiaowei Xu, Yiyu Shi, Jingtong Hu
Abstract	In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has also inspired to improve their implementations on hardware. While some practices of hardware machine-learning automation have achieved remarkable performance, the traditional design concept is still followed: a network architecture is first structured with excellent test accuracy, and then compressed and optimized to fit into a target platform. Such a design flow will easily lead to inferior local-optimal solutions. To address this problem, we propose a new framework to jointly explore the space of neural architecture, hardware implementation, and quantization. Our objective is to find a quantized architecture with the highest accuracy that is implementable on given hardware specifications. We employ FPGAs to implement and test our designs with limited loop-up tables (LUTs) and required throughput. Compared to the separate design/searching methods, our framework has demonstrated much better performance under strict specifications and generated designs of higher accuracy by 18% to 68% in the task of classifying CIFAR10 images. With 30,000 LUTs, a light-weight design is found to achieve 82.98% accuracy and 1293 images/second throughput, compared to which, under the same constraints, the traditional method even fails to find a valid solution.
Tasks	Neural Architecture Search, Quantization
Published	2019-10-31
URL	https://arxiv.org/abs/1911.00105v1
PDF	https://arxiv.org/pdf/1911.00105v1.pdf
PWC	https://paperswithcode.com/paper/on-neural-architecture-search-for-resource
Repo
Framework

Place Clustering-based Feature Recombination for Visual Place Recognition


Title	Place Clustering-based Feature Recombination for Visual Place Recognition
Authors	Qiang Zhai, Hong Cheng, Rui Huang, Huiqin Zhan
Abstract	Visual place recognition is an important problem in both computer vision and robotics, and image content changes caused by occlusion and viewpoint changes in natural scenes still pose challenges to place recognition. This paper aims at the problem by proposing novel feature recombination based on place clustering. Firstly, a general pyramid extension scheme, called Pyramid Principal Phases Feature (Tri-PF), is extracted based on the histogram feature. Further to maximize the role of the new feature, we evaluate the similarity by clustering images with a certain threshold as a ‘place’. Extensive experiments have been conducted to verify the effectiveness of the proposed approach and the results demonstrate that our method can achieve consistently better performance than state-of-the-art on two standard place recognition benchmarks.
Tasks	Visual Place Recognition
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11350v1
PDF	https://arxiv.org/pdf/1907.11350v1.pdf
PWC	https://paperswithcode.com/paper/place-clustering-based-feature-recombination
Repo
Framework

Solving Logic Grid Puzzles with an Algorithm that Imitates Human Behavior


Title	Solving Logic Grid Puzzles with an Algorithm that Imitates Human Behavior
Authors	Guillaume Escamocher, Barry O’Sullivan
Abstract	We present in this paper our solver for logic grid puzzles. The approach used by our algorithm mimics the way a human would try to solve the same problem. Every progress made during the solving process is accompanied by a detailed explanation of our program’s reasoning. Since this reasoning is based on the same heuristics that a human would employ, the user can easily follow the given explanation.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06636v1
PDF	https://arxiv.org/pdf/1910.06636v1.pdf
PWC	https://paperswithcode.com/paper/solving-logic-grid-puzzles-with-an-algorithm
Repo
Framework

Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables


Title	Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Authors	Yan Xu, Baoyuan Wu, Fumin Shen, Yanbo Fan, Yong Zhang, Heng Tao Shen, Wei Liu
Abstract	In this work, we study the robustness of a CNN+RNN based image captioning system being subjected to adversarial noises. We propose to fool an image captioning system to generate some targeted partial captions for an image polluted by adversarial noises, even the targeted captions are totally irrelevant to the image content. A partial caption indicates that the words at some locations in this caption are observed, while words at other locations are not restricted.It is the first work to study exact adversarial attacks of targeted partial captions. Due to the sequential dependencies among words in a caption, we formulate the generation of adversarial noises for targeted partial captions as a structured output learning problem with latent variables. Both the generalized expectation maximization algorithm and structural SVMs with latent variables are then adopted to optimize the problem. The proposed methods generate very successful at-tacks to three popular CNN+RNN based image captioning models. Furthermore, the proposed attack methods are used to understand the inner mechanism of image captioning systems, providing the guidance to further improve automatic image captioning systems towards human captioning.
Tasks	Adversarial Attack, Image Captioning
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04016v1
PDF	https://arxiv.org/pdf/1905.04016v1.pdf
PWC	https://paperswithcode.com/paper/exact-adversarial-attack-to-image-captioning
Repo
Framework

Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence


Title	Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence
Authors	Chen Zhao, Jiaqi Yang, Ke Xian, Zhiguo Cao, Xin Li
Abstract	Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction. Current state of the art in image feature matching has focused on establishing a single consistency in static scenes; by contrast, finding multiple consistencies in dynamic scenes has been under-researched. In this paper, we present an end-to-end optimization framework named “iterative clustering with Game-Theoretic Matching” (ic-GTM) for robust multi-consistency correspondence. The key idea is to formulate multi-consistency matching as a generalized clustering problem for an image pair. In our formulation, several local matching games are simultaneously carried out in different corresponding block pairs under the guidance of a novel payoff function consisting of both geometric and descriptive compatibility; the global matching results are further iteratively refined by clustering and thresholding with respect to a payoff matrix. We also propose three new metrics for evaluating the performance of multi-consistency image feature matching. Extensive experimental results have shown that the proposed framework significantly outperforms previous state-of-the-art approaches on both singleconsistency and multi-consistency datasets.
Tasks	3D Reconstruction, Object Recognition
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01497v1
PDF	https://arxiv.org/pdf/1909.01497v1.pdf
PWC	https://paperswithcode.com/paper/iterative-clustering-with-game-theoretic
Repo
Framework

MultiLock: Mobile Active Authentication based on Multiple Biometric and Behavioral Patterns


Title	MultiLock: Mobile Active Authentication based on Multiple Biometric and Behavioral Patterns
Authors	Alejandro Acien, Aythami Morales, Ruben Vera-Rodriguez, Julian Fierrez
Abstract	In this paper we evaluate mobile active authentication based on an ensemble of biometrics and behavior-based profiling signals. We consider seven different data channels and their combination. Touch dynamics (touch gestures and keystroking), accelerometer, gyroscope, WiFi, GPS location and app usage are all collected during human-mobile interaction to authenticate the users. We evaluate two approaches: one-time authentication and active authentication. In one-time authentication, we employ the information of all channels available during one session. For active authentication we take advantage of mobile user behavior across multiple sessions by updating a confidence value of the authentication score. Our experiments are conducted on the semi-uncontrolled UMDAA-02 database. This database comprises smartphone sensor signals acquired during natural human-mobile interaction. Our results show that different traits can be complementary and multimodal systems clearly increase the performance with accuracies ranging from 82.2% to 97.1% depending on the authentication scenario.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10312v1
PDF	http://arxiv.org/pdf/1901.10312v1.pdf
PWC	https://paperswithcode.com/paper/multilock-mobile-active-authentication-based
Repo
Framework

Energy-Efficient Radio Resource Allocation for Federated Edge Learning


Title	Energy-Efficient Radio Resource Allocation for Federated Edge Learning
Authors	Qunsong Zeng, Yuqing Du, Kin K. Leung, Kaibin Huang
Abstract	Edge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this work, we explore the new direction of energy-efficient radio resource management (RRM) for FEEL. To reduce devices’ energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling. They adapt to devices’ channel states and computation capacities so as to reduce their sum energy consumption while warranting learning performance. In contrast with the traditional rate-maximization designs, the derived optimal policies allocate more bandwidth to those scheduled devices with weaker channels or poorer computation capacities, which are the bottlenecks of synchronized model updates in FEEL. On the other hand, the scheduling priority function derived in closed form gives preferences to devices with better channels and computation capacities. Substantial energy reduction contributed by the proposed strategies is demonstrated in learning experiments.
Tasks
Published	2019-07-13
URL	https://arxiv.org/abs/1907.06040v1
PDF	https://arxiv.org/pdf/1907.06040v1.pdf
PWC	https://paperswithcode.com/paper/energy-efficient-radio-resource-allocation
Repo
Framework

Ordered Sets for Data Analysis


Title	Ordered Sets for Data Analysis
Authors	Sergei O. Kuznetsov
Abstract	This book dwells on mathematical and algorithmic issues of data analysis based on generality order of descriptions and respective precision. To speak of these topics correctly, we have to go some way getting acquainted with the important notions of relation and order theory. On the one hand, data often have a complex structure with natural order on it. On the other hand, many symbolic methods of data analysis and machine learning allow to compare the obtained classifiers w.r.t. their generality, which is also an order relation. Efficient algorithms are very important in data analysis, especially when one deals with big data, so scalability is a real issue. That is why we analyze the computational complexity of algorithms and problems of data analysis. We start from the basic definitions and facts of algorithmic complexity theory and analyze the complexity of various tools of data analysis we consider. The tools and methods of data analysis, like computing taxonomies, groups of similar objects (concepts and n-clusters), dependencies in data, classification, etc., are illustrated with applications in particular subject domains, from chemoinformatics to text mining and natural language processing.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.11341v1
PDF	https://arxiv.org/pdf/1908.11341v1.pdf
PWC	https://paperswithcode.com/paper/ordered-sets-for-data-analysis
Repo
Framework