Paper Group ANR 1715
Machine Learning as Ecology. DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision. Understanding the Importance of Single Directions via Representative Substitution. A Self-consistent-field Iteration for Orthogonal Canonical Correlation Analysis. PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degrad …
Machine Learning as Ecology
| Title | Machine Learning as Ecology |
| Authors | Owen Howell, Cui Wenping, Robert Marsland III, Pankaj Mehta |
| Abstract | Machine learning methods have had spectacular success on numerous problems. Here we show that a prominent class of learning algorithms - including Support Vector Machines (SVMs) – have a natural interpretation in terms of ecological dynamics. We use these ideas to design new online SVM algorithms that exploit ecological invasions, and benchmark performance using the MNIST dataset. Our work provides a new ecological lens through which we can view statistical learning and opens the possibility of designing ecosystems for machine learning. Supplemental code is found at https://github.com/owenhowell20/EcoSVM. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00868v2 |
| https://arxiv.org/pdf/1908.00868v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-as-ecology |
| Repo | |
| Framework | |
DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
| Title | DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision |
| Authors | Duc Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox |
| Abstract | Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels. In this work, we propose a two-stage mechanism for robust unsupervised object saliency prediction, where the first stage involves refinement of the noisy pseudo labels generated from different handcrafted methods. Each handcrafted method is substituted by a deep network that learns to generate the pseudo labels. These labels are refined incrementally in multiple iterations via our proposed self-supervision technique. In the second stage, the refined labels produced from multiple networks representing multiple saliency methods are used to train the actual saliency detection network. We show that this self-learning procedure outperforms all the existing unsupervised methods over different datasets. Results are even comparable to those of fully-supervised state-of-the-art approaches. |
| Tasks | Object Detection, Saliency Detection, Saliency Prediction, Salient Object Detection |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13055v3 |
| https://arxiv.org/pdf/1909.13055v3.pdf | |
| PWC | https://paperswithcode.com/paper/deepusps-deep-robust-unsupervised-saliency |
| Repo | |
| Framework | |
Understanding the Importance of Single Directions via Representative Substitution
| Title | Understanding the Importance of Single Directions via Representative Substitution |
| Authors | Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li |
| Abstract | Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid much attention given their fundamental role. However, recent research (Morcos et al. 2018) presented a counterintuitive phenomenon, which suggests that an individual unit with high class selectivity, called interpretable units, has poor contributions to generalization of DNNs. In this work, we provide a new perspective to understand this counterintuitive phenomenon, which makes sense when we introduce Representative Substitution (RS). Instead of individually selective units with classes, the RS refers to the independence of a unit’s representations in the same layer without any annotation. Our experiments demonstrate that interpretable units have high RS which are not critical to network’s generalization. The RS provides new insights into the interpretation of DNNs and suggests that we need to focus on the independence and relationship of the representations. |
| Tasks | |
| Published | 2019-01-20 |
| URL | https://arxiv.org/abs/1911.05586v1 |
| https://arxiv.org/pdf/1911.05586v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-the-importance-of-single-1 |
| Repo | |
| Framework | |
A Self-consistent-field Iteration for Orthogonal Canonical Correlation Analysis
| Title | A Self-consistent-field Iteration for Orthogonal Canonical Correlation Analysis |
| Authors | Leihong Zhang, Li Wang, Zhaojun Bai, Ren-cang Li |
| Abstract | We propose an efficient algorithm for solving orthogonal canonical correlation analysis (OCCA) in the form of trace-fractional structure and orthogonal linear projections. Even though orthogonality has been widely used and proved to be a useful criterion for pattern recognition and feature extraction, existing methods for solving OCCA problem are either numerical unstable by relying on a deflation scheme, or less efficient by directly using generic optimization methods. In this paper, we propose an alternating numerical scheme whose core is the sub-maximization problem in the trace-fractional form with an orthogonal constraint. A customized self-consistent-field (SCF) iteration for this sub-maximization problem is devised. It is proved that the SCF iteration is globally convergent to a KKT point and that the alternating numerical scheme always converges. We further formulate a new trace-fractional maximization problem for orthogonal multiset CCA (OMCCA) and then propose an efficient algorithm with an either Jacobi-style or Gauss-Seidel-style updating scheme based on the same SCF iteration. Extensive experiments are conducted to evaluate the proposed algorithms against existing methods including two real world applications: multi-label classification and multi-view feature extraction. Experimental results show that our methods not only perform competitively to or better than baselines but also are more efficient. |
| Tasks | Multi-Label Classification |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11527v1 |
| https://arxiv.org/pdf/1909.11527v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-consistent-field-iteration-for |
| Repo | |
| Framework | |
PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degradation
| Title | PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degradation |
| Authors | Dahuin Jung, Ho Bae, Hyun-Soo Choi, Sungroh Yoon |
| Abstract | It is difficult to detect and remove secret images that are hidden in natural images using deep-learning algorithms. Our technique is the first work to effectively disable covert communications and transactions that use deep-learning steganography. We address the problem by exploiting sophisticated pixel distributions and edge areas of images using a deep neural network. Based on the given information, we adaptively remove secret information at the pixel level. We also introduce a new quantitative metric called destruction rate since the decoding method of deep-learning steganography is approximate (lossy), which is different from conventional steganography. We evaluate our technique using three public benchmarks in comparison with conventional steganalysis methods and show that the decoding rate improves by 10 ~ 20%. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10905v1 |
| http://arxiv.org/pdf/1902.10905v1.pdf | |
| PWC | https://paperswithcode.com/paper/pixelsteganalysis-pixel-wise-hidden |
| Repo | |
| Framework | |
On the Convergence Proof of AMSGrad and a New Version
| Title | On the Convergence Proof of AMSGrad and a New Version |
| Authors | Tran Thi Phuong, Le Trieu Phong |
| Abstract | The adaptive moment estimation algorithm Adam (Kingma and Ba) is a popular optimizer in the training of deep neural networks. However, Reddi et al. have recently shown that the convergence proof of Adam is problematic and proposed a variant of Adam called AMSGrad as a fix. In this paper, we show that the convergence proof of AMSGrad is also problematic. Concretely, the problem in the convergence proof of AMSGrad is in handling the hyper-parameters, treating them as equal while they are not. This is also the neglected issue in the convergence proof of Adam. We provide an explicit counter-example of a simple convex optimization setting to show this neglected issue. Depending on manipulating the hyper-parameters, we present various fixes for this issue. We provide a new convergence proof for AMSGrad as the first fix. We also propose a new version of AMSGrad called AdamX as another fix. Our experiments on the benchmark dataset also support our theoretical results. |
| Tasks | |
| Published | 2019-04-07 |
| URL | https://arxiv.org/abs/1904.03590v4 |
| https://arxiv.org/pdf/1904.03590v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-proof-of-amsgrad-and-a-new |
| Repo | |
| Framework | |
CS563-QA: A Collection for Evaluating Question Answering Systems
| Title | CS563-QA: A Collection for Evaluating Question Answering Systems |
| Authors | Katerina Papantoniou, Yannis Tzitzikas |
| Abstract | Question Answering (QA) is a challenging topic since it requires tackling the various difficulties of natural language understanding. Since evaluation is important not only for identifying the strong and weak points of the various techniques for QA, but also for facilitating the inception of new methods and techniques, in this paper we present a collection for evaluating QA methods over free text that we have created. Although it is a small collection, it contains cases of increasing difficulty, therefore it has an educational value and it can be used for rapid evaluation of QA systems. |
| Tasks | Question Answering |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01611v1 |
| https://arxiv.org/pdf/1907.01611v1.pdf | |
| PWC | https://paperswithcode.com/paper/cs563-qa-a-collection-for-evaluating-question |
| Repo | |
| Framework | |
Benchmarking Regression Methods: A comparison with CGAN
| Title | Benchmarking Regression Methods: A comparison with CGAN |
| Authors | Karan Aggarwal, Matthieu Kirchmeyer, Pranjul Yadav, S. Sathiya Keerthi, Patrick Gallinari |
| Abstract | In recent years, impressive progress has been made in the design of implicit probabilistic models via Generative Adversarial Networks (GAN) and its extension, the Conditional GAN (CGAN). Excellent solutions have been demonstrated mostly in image processing applications which involve large, continuous output spaces. There is almost no application of these powerful tools to problems having small dimensional output spaces. Regression problems involving the inductive learning of a map, $y=f(x,z)$, $z$ denoting noise, $f:\mathbb{R}^n\times \mathbb{R}^k \rightarrow \mathbb{R}^m$, with $m$ small (e.g., $m=1$ or just a few) is one good case in point. The standard approach to solve regression problems is to probabilistically model the output $y$ as the sum of a mean function $m(x)$ and a noise term $z$; it is also usual to take the noise to be a Gaussian. These are done for convenience sake so that the likelihood of observed data is expressible in closed form. In the real world, on the other hand, stochasticity of the output is usually caused by missing or noisy input variables. Such a real world situation is best represented using an implicit model in which an extra noise vector, $z$ is included with $x$ as input. CGAN is naturally suited to design such implicit models. This paper makes the first step in this direction and compares the existing regression methods with CGAN. We notice however, that the existing methods like mixture density networks (MDN) and XGBoost do quite well compared to CGAN in terms of likelihood and mean absolute error, respectively. Both these methods are comparatively easier to train than CGANs. CGANs need more innovation to have a comparable modeling and ease-of-training with respect to the existing regression solvers. In summary, for modeling uncertainty MDNs are better while XGBoost is better for the cases where accurate prediction is more important. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12868v5 |
| https://arxiv.org/pdf/1905.12868v5.pdf | |
| PWC | https://paperswithcode.com/paper/regression-with-conditional-gan |
| Repo | |
| Framework | |
Examining UK drill music through sentiment trajectory analysis
| Title | Examining UK drill music through sentiment trajectory analysis |
| Authors | Bennett Kleinberg, Paul McFarlane |
| Abstract | This paper presents how techniques from natural language processing can be used to examine the sentiment trajectories of gang-related drill music in the United Kingdom (UK). This work is important because key public figures are loosely making controversial linkages between drill music and recent escalations in youth violence in London. Thus, this paper examines the dynamic use of sentiment in gang-related drill music lyrics. The findings suggest two distinct sentiment use patterns and statistical analyses revealed that lyrics with a markedly positive tone attract more views and engagement on YouTube than negative ones. Our work provides the first empirical insights into the language use of London drill music, and it can, therefore, be used in future studies and by policymakers to help understand the alleged drill-gang nexus. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01324v1 |
| https://arxiv.org/pdf/1911.01324v1.pdf | |
| PWC | https://paperswithcode.com/paper/examining-uk-drill-music-through-sentiment |
| Repo | |
| Framework | |
Recognizing Human Internal States: A Conceptor-Based Approach
| Title | Recognizing Human Internal States: A Conceptor-Based Approach |
| Authors | Madeleine Bartlett, Daniel Hernandez Garcia, Serge Thill, Tony Belpaeme |
| Abstract | The past few decades has seen increased interest in the application of social robots to interventions for Autism Spectrum Disorder as behavioural coaches [4]. We consider that robots embedded in therapies could also provide quantitative diagnostic information by observing patient behaviours. The social nature of ASD symptoms means that, to achieve this, robots need to be able to recognize the internal states their human interaction partners are experiencing, e.g. states of confusion, engagement etc. Approaching this problem can be broken down into two questions: (1) what information, accessible to robots, can be used to recognize internal states, and (2) how can a system classify internal states such that it allows for sufficiently detailed diagnostic information? In this paper we discuss these two questions in depth and propose a novel, conceptor-based classifier. We report the initial results of this system in a proof-of-concept study and outline plans for future work. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.04747v1 |
| https://arxiv.org/pdf/1909.04747v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-human-internal-states-a-conceptor |
| Repo | |
| Framework | |
Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication
| Title | Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication |
| Authors | Ali Taleb Zadeh Kasgari, Walid Saad, Mohammad Mozaffari, H. Vincent Poor |
| Abstract | In this paper, a novel experienced deep reinforcement learning (deep-RL) framework is proposed to provide model-free resource allocation for ultra reliable low latency communication (URLLC). The proposed, experienced deep-RL framework can guarantee high end-to-end reliability and low end-to-end latency, under explicit data rate constraints, for each wireless without any models of or assumptions on the users’ traffic. In particular, in order to enable the deep-RL framework to account for extreme network conditions and operate in highly reliable systems, a new approach based on generative adversarial networks (GANs) is proposed. This GAN approach is used to pre-train the deep-RL framework using a mix of real and synthetic data, thus creating an experienced deep-RL framework that has been exposed to a broad range of network conditions. Formally, the URLLC resource allocation problem is posed as a power minimization problem under reliability, latency, and rate constraints. To solve this problem using experienced deep-RL, first, the rate of each user is determined. Then, these rates are mapped to the resource block and power allocation vectors of the studied wireless system. Finally, the end-to-end reliability and latency of each user are used as feedback to the deep-RL framework. It is then shown that at the fixed-point of the deep-RL algorithm, the reliability and latency of the users are near-optimal. Moreover, for the proposed GAN approach, a theoretical limit for the generator output is analytically derived. Simulation results show how the proposed approach can achieve near-optimal performance within the rate-reliability-latency region, depending on the network and service requirements. The results also show that the proposed experienced deep-RL framework is able to remove the transient training time that makes conventional deep-RL methods unsuitable for URLLC. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.03264v1 |
| https://arxiv.org/pdf/1911.03264v1.pdf | |
| PWC | https://paperswithcode.com/paper/experienced-deep-reinforcement-learning-with |
| Repo | |
| Framework | |
Deep Conservative Policy Iteration
| Title | Deep Conservative Policy Iteration |
| Authors | Nino Vieillard, Olivier Pietquin, Matthieu Geist |
| Abstract | Conservative Policy Iteration (CPI) is a founding algorithm of Approximate Dynamic Programming (ADP). Its core principle is to stabilize greediness through stochastic mixtures of consecutive policies. It comes with strong theoretical guarantees, and inspired approaches in deep Reinforcement Learning (RL). However, CPI itself has rarely been implemented, never with neural networks, and only experimented on toy problems. In this paper, we show how CPI can be practically combined with deep RL with discrete actions. We also introduce adaptive mixture rates inspired by the theory. We experiment thoroughly the resulting algorithm on the simple Cartpole problem, and validate the proposed method on a representative subset of Atari games. Overall, this work suggests that revisiting classic ADP may lead to improved and more stable deep RL algorithms. |
| Tasks | Atari Games |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09784v2 |
| https://arxiv.org/pdf/1906.09784v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-conservative-policy-iteration |
| Repo | |
| Framework | |
Learning Powerful Policies by Using Consistent Dynamics Model
| Title | Learning Powerful Policies by Using Consistent Dynamics Model |
| Authors | Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang |
| Abstract | Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based approaches lead to compounding errors' when the model is unrolled step by step. Essentially, the state transitions that the learner predicts (by unrolling the model for multiple steps) and the state transitions that the learner experiences (by acting in the environment) may not be consistent. There is enough evidence that humans build a model of the environment, not only by observing the environment but also by interacting with the environment. Interaction with the environment allows humans to carry out experiments: taking actions that help uncover true causal relationships which can be used for building better dynamics models. Analogously, we would expect such interactions to be helpful for a learning agent while learning to model the environment dynamics. In this paper, we build upon this intuition by using an auxiliary cost function to ensure consistency between what the agent observes (by acting in the real world) and what it imagines (by acting in the learned’ world). We consider several tasks - Mujoco based control tasks and Atari games - and show that the proposed approach helps to train powerful policies and better dynamics models. |
| Tasks | Atari Games |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04355v1 |
| https://arxiv.org/pdf/1906.04355v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-powerful-policies-by-using |
| Repo | |
| Framework | |
Combined analysis of coronary arteries and the left ventricular myocardium in cardiac CT angiography for detection of patients with functionally significant stenosis
| Title | Combined analysis of coronary arteries and the left ventricular myocardium in cardiac CT angiography for detection of patients with functionally significant stenosis |
| Authors | Majd Zreik, Tim Leiner, Nadieh Khalili, Robbert W. van Hamersvelt, Jelmer M. Wolterink, Michiel Voskuil, Max A. Viergever, Ivana Išgum |
| Abstract | Treatment of patients with obstructive coronary artery disease is guided by the functional significance of a coronary artery stenosis. Fractional flow reserve (FFR), measured during invasive coronary angiography (ICA), is considered the gold standard to define the functional significance of a coronary stenosis. Here, we present a method for non-invasive detection of patients with functionally significant coronary artery stenosis, combining analysis of the coronary artery tree and the left ventricular (LV) myocardium in cardiac CT angiography (CCTA) images. We retrospectively collected CCTA scans of 126 patients who underwent invasive FFR measurements, to determine the functional significance of coronary stenoses. We combine our previous works for the analysis of the complete coronary artery tree and the LV myocardium: Coronary arteries are encoded by two disjoint convolutional autoencoders (CAEs) and the LV myocardium is characterized by a convolutional neural network (CNN) and a CAE. Thereafter, using the extracted encodings of all coronary arteries and the LV myocardium, patients are classified according to the presence of functionally significant stenosis, as defined by the invasively measured FFR. To handle the varying number of coronary arteries in a patient, the classification is formulated as a multiple instance learning problem and is performed using an attention-based neural network. Cross-validation experiments resulted in an average area under the receiver operating characteristic curve of $0.74 \pm 0.01$, and showed that the proposed combined analysis outperformed the analysis of the coronary arteries or the LV myocardium only. The results demonstrate the feasibility of combining the analyses of the complete coronary artery tree and the LV myocardium in CCTA images for the detection of patients with functionally significant stenosis in coronary arteries. |
| Tasks | Multiple Instance Learning |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.04940v1 |
| https://arxiv.org/pdf/1911.04940v1.pdf | |
| PWC | https://paperswithcode.com/paper/combined-analysis-of-coronary-arteries-and |
| Repo | |
| Framework | |
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension
| Title | X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension |
| Authors | Mostafa Abdou, Cezar Sas, Rahul Aralikatte, Isabelle Augenstein, Anders Søgaard |
| Abstract | Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in different languages. Exploiting this, we introduce a new multilingual dataset (X-WikiRE), framing relation extraction as a multilingual machine reading problem. We show that by leveraging this resource it is possible to robustly transfer models cross-lingually and that multilingual support significantly improves (zero-shot) relation extraction, enabling the population of low-resourced KBs from their well-populated counterparts. |
| Tasks | Reading Comprehension, Relation Extraction |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05111v2 |
| https://arxiv.org/pdf/1908.05111v2.pdf | |
| PWC | https://paperswithcode.com/paper/x-wikire-a-large-multilingual-resource-for |
| Repo | |
| Framework | |
