Paper Group ANR 934
SURFACE: Semantically Rich Fact Validation with Explanations. An Ensemble Generation Method Based on Instance Hardness. WiPIN: Operation-free Passive Person Identification Using Wi-Fi Signals. Composable Core-sets for Determinant Maximization Problems via Spectral Spanners. A Geometric Approach of Gradient Descent Algorithms in Neural Networks. Fea …
SURFACE: Semantically Rich Fact Validation with Explanations
| Title | SURFACE: Semantically Rich Fact Validation with Explanations |
| Authors | Ankur Padia, Francis Ferraro, Tim Finin |
| Abstract | Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions. The recent FEVER task asked participants to classify input sentences as either SUPPORTED, REFUTED or NotEnoughInfo using Wikipedia as a source of true facts. SURFACE does this task and explains its decision through a selection of sentences from the trusted source. Our multi-task neural approach uses semantic lexical frames from FrameNet to jointly (i) find relevant evidential sentences in the trusted source and (ii) use them to classify the input sentence’s veracity. An evaluation of our efficient three-parameter model on the FEVER dataset showed an improvement of 90% over the state-of-the-art baseline on retrieving relevant sentences and a 70% relative improvement in classification. |
| Tasks | |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1810.13223v1 |
| http://arxiv.org/pdf/1810.13223v1.pdf | |
| PWC | https://paperswithcode.com/paper/surface-semantically-rich-fact-validation |
| Repo | |
| Framework | |
An Ensemble Generation Method Based on Instance Hardness
| Title | An Ensemble Generation Method Based on Instance Hardness |
| Authors | Felipe N. Walmsley, George D. C. Cavalcanti, Dayvid V. R. Oliveira, Rafael M. O. Cruz, Robert Sabourin |
| Abstract | In Machine Learning, ensemble methods have been receiving a great deal of attention. Techniques such as Bagging and Boosting have been successfully applied to a variety of problems. Nevertheless, such techniques are still susceptible to the effects of noise and outliers in the training data. We propose a new method for the generation of pools of classifiers based on Bagging, in which the probability of an instance being selected during the resampling process is inversely proportional to its instance hardness, which can be understood as the likelihood of an instance being misclassified, regardless of the choice of classifier. The goal of the proposed method is to remove noisy data without sacrificing the hard instances which are likely to be found on class boundaries. We evaluate the performance of the method in nineteen public data sets, and compare it to the performance of the Bagging and Random Subspace algorithms. Our experiments show that in high noise scenarios the accuracy of our method is significantly better than that of Bagging. |
| Tasks | |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1804.07419v2 |
| http://arxiv.org/pdf/1804.07419v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-ensemble-generation-method-based-on |
| Repo | |
| Framework | |
WiPIN: Operation-free Passive Person Identification Using Wi-Fi Signals
| Title | WiPIN: Operation-free Passive Person Identification Using Wi-Fi Signals |
| Authors | Fei Wang, Jinsong Han, Feng Lin, Kui Ren |
| Abstract | Wi-Fi signals-based person identification attracts increasing attention in the booming Internet-of-Things era mainly due to its pervasiveness and passiveness. Most previous work applies gaits extracted from WiFi distortions caused by the person walking to achieve the identification. However, to extract useful gait, a person must walk along a pre-defined path for several meters, which requires user high collaboration and increases identification time overhead, thus limiting use scenarios. Moreover, gait based work has severe shortcoming in identification performance, especially when the user volume is large. In order to eliminate the above limitations, in this paper, we present an operation-free person identification system, namely WiPIN, that requires least user collaboration and achieves good performance. WiPIN is based on an entirely new insight that Wi-Fi signals would carry person body information when propagating through the body, which is potentially discriminated for person identification. Then we demonstrate the feasibility on commodity off-the-shelf Wi-Fi devices by well-designed signal pre-processing, feature extraction, and identity matching algorithms. Results show that WiPIN achieves 92% identification accuracy over 30 users, high robustness to various experimental settings, and low identifying time overhead, i.e., less than 300ms. |
| Tasks | Person Identification |
| Published | 2018-10-06 |
| URL | https://arxiv.org/abs/1810.04106v2 |
| https://arxiv.org/pdf/1810.04106v2.pdf | |
| PWC | https://paperswithcode.com/paper/wipin-operation-free-person-identification |
| Repo | |
| Framework | |
Composable Core-sets for Determinant Maximization Problems via Spectral Spanners
| Title | Composable Core-sets for Determinant Maximization Problems via Spectral Spanners |
| Authors | Piotr Indyk, Sepideh Mahabadi, Shayan Oveis Gharan, Alireza Rezaei |
| Abstract | We study a spectral generalization of classical combinatorial graph spanners to the spectral setting. Given a set of vectors $V\subseteq \Re^d$, we say a set $U\subseteq V$ is an $\alpha$-spectral spanner if for all $v\in V$ there is a probability distribution $\mu_v$ supported on $U$ such that $$vv^\intercal \preceq \alpha\cdot\mathbb{E}_{u\sim\mu_v} uu^\intercal.$$ We show that any set $V$ has an $\tilde{O}(d)$-spectral spanner of size $\tilde{O}(d)$ and this bound is almost optimal in the worst case. We use spectral spanners to study composable core-sets for spectral problems. We show that for many objective functions one can use a spectral spanner, independent of the underlying functions, as a core-set and obtain almost optimal composable core-sets. For example, for the determinant maximization problem we obtain an $\tilde{O}(k)^k$-composable core-set and we show that this is almost optimal in the worst case. Our algorithm is a spectral analogue of the classical greedy algorithm for finding (combinatorial) spanners in graphs. We expect that our spanners find many other applications in distributed or parallel models of computation. Our proof is spectral. As a side result of our techniques, we show that the rank of diagonally dominant lower-triangular matrices are robust under `small perturbations’ which could be of independent interests. | |
| Tasks | |
| Published | 2018-07-31 |
| URL | https://arxiv.org/abs/1807.11648v2 |
| https://arxiv.org/pdf/1807.11648v2.pdf | |
| PWC | https://paperswithcode.com/paper/composable-core-sets-for-determinant |
| Repo | |
| Framework | |
A Geometric Approach of Gradient Descent Algorithms in Neural Networks
| Title | A Geometric Approach of Gradient Descent Algorithms in Neural Networks |
| Authors | Yacine Chitour, Zhenyu Liao, Romain Couillet |
| Abstract | In this paper, we present an original geometric framework to analyze the convergence properties of gradient descent trajectories in the context of linear neural networks. Built upon a key invariance property induced by the network structure, we propose a conjecture called \emph{overfitting conjecture} stating that, for almost every training data, the corresponding gradient descent trajectory converges to a global minimum, for almost every initial condition. This would imply that, for linear neural networks of an arbitrary number of hidden layers, the solution achieved by simple gradient descent algorithm is equivalent to that of least square estimation. Our first result consists in establishing, in the case of linear networks of arbitrary depth, convergence of gradient descent trajectories to critical points of the loss function. Our second result is the proof of the \emph{overfitting conjecture} in the case of single-hidden-layer linear networks with an argument based on the notion of normal hyperbolicity and under a generic property on the training data (i.e., holding for almost every training data). |
| Tasks | |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03568v2 |
| http://arxiv.org/pdf/1811.03568v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-approach-of-gradient-descent |
| Repo | |
| Framework | |
Features and Machine Learning for Correlating and Classifying between Brain Areas and Dyslexia
| Title | Features and Machine Learning for Correlating and Classifying between Brain Areas and Dyslexia |
| Authors | Alex Frid, Larry M. Manevitz |
| Abstract | We develop a method that is based on processing gathered Event Related Potentials (ERP) signals and the use of machine learning technique for multivariate analysis (i.e. classification) that we apply in order to analyze the differences between Dyslexic and Skilled readers. No human intervention is needed in the analysis process. This is the state of the art results for automatic identification of Dyslexic readers using a Lexical Decision Task. We use mathematical and machine learning based techniques to automatically discover novel complex features that (i) allow for reliable distinction between Dyslexic and Normal Control Skilled readers and (ii) to validate the assumption that the most of the differences between Dyslexic and Skilled readers located in the left hemisphere. Interestingly, these tools also pointed to the fact that High Pass signals (typically considered as “noise” during ERP/EEG analyses) in fact contains significant relevant information. Finally, the proposed scheme can be used for analysis of any ERP based studies. |
| Tasks | EEG |
| Published | 2018-12-27 |
| URL | http://arxiv.org/abs/1812.10622v2 |
| http://arxiv.org/pdf/1812.10622v2.pdf | |
| PWC | https://paperswithcode.com/paper/features-and-machine-learning-for-correlating |
| Repo | |
| Framework | |
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
| Title | On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport |
| Authors | Lenaic Chizat, Francis Bach |
| Abstract | Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture of particles and a continuous-time gradient descent is performed on their weights and positions. This is an idealization of the usual way to train neural networks with a large hidden layer. We show that, when initialized correctly and in the many-particle limit, this gradient flow, although non-convex, converges to global minimizers. The proof involves Wasserstein gradient flows, a by-product of optimal transport theory. Numerical experiments show that this asymptotic behavior is already at play for a reasonable number of particles, even in high dimension. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09545v2 |
| http://arxiv.org/pdf/1805.09545v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-global-convergence-of-gradient-descent |
| Repo | |
| Framework | |
Two Stream Self-Supervised Learning for Action Recognition
| Title | Two Stream Self-Supervised Learning for Action Recognition |
| Authors | Ahmed Taha, Moustafa Meshry, Xitong Yang, Yi-Ting Chen, Larry Davis |
| Abstract | We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and temporal representation learning. Our task is formulated as both a sequence verification and spatio-temporal alignment tasks. The former task requires motion temporal structure understanding while the latter couples the learned motion with the spatial representation. The self-supervised pre-trained weights effectiveness is validated on the action recognition task. Quantitative evaluation shows the self-supervised approach competence on three datasets: HMDB51, UCF101, and Honda driving dataset (HDD). Further investigations to boost performance and generalize validity are still required. |
| Tasks | Representation Learning, Temporal Action Localization |
| Published | 2018-06-16 |
| URL | http://arxiv.org/abs/1806.07383v1 |
| http://arxiv.org/pdf/1806.07383v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-stream-self-supervised-learning-for |
| Repo | |
| Framework | |
Exploiting Wireless Channel State Information Structures Beyond Linear Correlations: A Deep Learning Approach
| Title | Exploiting Wireless Channel State Information Structures Beyond Linear Correlations: A Deep Learning Approach |
| Authors | Zhiyuan Jiang, Sheng Chen, Andreas F. Molisch, Rath Vannithamby, Sheng Zhou, Zhisheng Niu |
| Abstract | Knowledge of information about the propagation channel in which a wireless system operates enables better, more efficient approaches for signal transmissions. Therefore, channel state information (CSI) plays a pivotal role in the system performance. The importance of CSI is in fact growing in the upcoming 5G and beyond systems, e.g., for the implementation of massive multiple-input multiple-output (MIMO). However, the acquisition of timely and accurate CSI has long been considered as a major issue, and becomes increasingly challenging due to the need for obtaining CSI of many antenna elements in massive MIMO systems. To cope with this challenge, existing works mainly focus on exploiting linear structures of CSI, such as CSI correlations in the spatial domain, to achieve dimensionality reduction. In this article, we first systematically review the state-of-the-art on CSI structure exploitation; then extend to seek for deeper structures that enable remote CSI inference wherein a data-driven deep neural network (DNN) approach is necessary due to model inadequacy. We develop specific DNN designs suitable for CSI data. Case studies are provided to demonstrate great potential in this direction for future performance enhancement. |
| Tasks | Dimensionality Reduction |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00541v1 |
| http://arxiv.org/pdf/1812.00541v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-wireless-channel-state-information |
| Repo | |
| Framework | |
Superrational types
| Title | Superrational types |
| Authors | Fernando Tohmé, Ignacio Viglizzo |
| Abstract | We present a formal analysis of Douglas Hofstadter’s concept of \emph{superrationality}. We start by defining superrationally justifiable actions, and study them in symmetric games. We then model the beliefs of the players, in a way that leads them to different choices than the usual assumption of rationality by restricting the range of conceivable choices. These beliefs are captured in the formal notion of \emph{type} drawn from epistemic game theory. The theory of coalgebras is used to frame type spaces and to account for the existence of some of them. We find conditions that guarantee superrational outcomes. |
| Tasks | |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1802.06888v1 |
| http://arxiv.org/pdf/1802.06888v1.pdf | |
| PWC | https://paperswithcode.com/paper/superrational-types |
| Repo | |
| Framework | |
Practical Challenges in Explicit Ethical Machine Reasoning
| Title | Practical Challenges in Explicit Ethical Machine Reasoning |
| Authors | Louise Dennis, Michael Fisher |
| Abstract | We examine implemented systems for ethical machine reasoning with a view to identifying the practical challenges (as opposed to philosophical challenges) posed by the area. We identify a need for complex ethical machine reasoning not only to be multi-objective, proactive, and scrutable but that it must draw on heterogeneous evidential reasoning. We also argue that, in many cases, it needs to operate in real time and be verifiable. We propose a general architecture involving a declarative ethical arbiter which draws upon multiple evidential reasoners each responsible for a particular ethical feature of the system’s environment. We claim that this architecture enables some separation of concerns among the practical challenges that ethical machine reasoning poses. |
| Tasks | |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01422v1 |
| http://arxiv.org/pdf/1801.01422v1.pdf | |
| PWC | https://paperswithcode.com/paper/practical-challenges-in-explicit-ethical |
| Repo | |
| Framework | |
An Integrated Inverse Space Sparse Representation Framework for Tumor Classification
| Title | An Integrated Inverse Space Sparse Representation Framework for Tumor Classification |
| Authors | Xiaohui Yang, Wenming Wu, Yunmei Chen, Xianqi Li, Juan Zhang, Dan Long, Lijun Yang |
| Abstract | Microarray gene expression data-based tumor classification is an active and challenging issue. In this paper, an integrated tumor classification framework is presented, which aims to exploit information in existing available samples, and focuses on the small sample problem and unbalanced classification problem. Firstly, an inverse space sparse representation based classification (ISSRC) model is proposed by considering the characteristics of gene-based tumor data, such as sparsity and a small number of training samples. A decision information factors (DIF)-based gene selection method is constructed to enhance the representation ability of the ISSRC. It is worth noting that the DIF is established from reducing clinical misdiagnosis rate and dimension of small sample data. For further improving the representation ability and classification stability of the ISSRC, feature learning is conducted on the selected gene subset. The feature learning method is constructed by complementing the advantages of non-negative matrix factorization (NMF) and deep learning. Without confusion, the ISSRC combined with gene selection and feature learning is called the integrated ISSRC, whose stability, optimization and the corresponding convergence are analyzed. Extensive experiments on six public microarray gene expression datasets show the integrated ISSRC-based tumor classification framework is superior to classical and state-of-the-art methods. There are significant improvements in classification accuracy, specificity and sensitivity, whether there is a tumor in the early diagnosis, what kind of tumor, or whether metastasis occurs after tumor surgery. |
| Tasks | Sparse Representation-based Classification |
| Published | 2018-03-09 |
| URL | http://arxiv.org/abs/1803.03562v4 |
| http://arxiv.org/pdf/1803.03562v4.pdf | |
| PWC | https://paperswithcode.com/paper/an-integrated-inverse-space-sparse |
| Repo | |
| Framework | |
Skin Disease Classification versus Skin Lesion Characterization: Achieving Robust Diagnosis using Multi-label Deep Neural Networks
| Title | Skin Disease Classification versus Skin Lesion Characterization: Achieving Robust Diagnosis using Multi-label Deep Neural Networks |
| Authors | Haofu Liao, Yuncheng Li, Jiebo Luo |
| Abstract | In this study, we investigate what a practically useful approach is in order to achieve robust skin disease diagnosis. A direct approach is to target the ground truth diagnosis labels, while an alternative approach instead focuses on determining skin lesion characteristics that are more visually consistent and discernible. We argue that, for computer-aided skin disease diagnosis, it is both more realistic and more useful that lesion type tags should be considered as the target of an automated diagnosis system such that the system can first achieve a high accuracy in describing skin lesions, and in turn facilitate disease diagnosis using lesion characteristics in conjunction with other evidence. To further meet such an objective, we employ convolutional neural networks (CNNs) for both the disease-targeted and lesion-targeted classifications. We have collected a large-scale and diverse dataset of 75,665 skin disease images from six publicly available dermatology atlantes. Then we train and compare both disease-targeted and lesion-targeted classifiers, respectively. For disease-targeted classification, only 27.6% top-1 accuracy and 57.9% top-5 accuracy are achieved with a mean average precision (mAP) of 0.42. In contrast, for lesion-targeted classification, we can achieve a much higher mAP of 0.70. |
| Tasks | |
| Published | 2018-12-09 |
| URL | https://arxiv.org/abs/1812.03520v2 |
| https://arxiv.org/pdf/1812.03520v2.pdf | |
| PWC | https://paperswithcode.com/paper/skin-disease-classification-versus-skin |
| Repo | |
| Framework | |
What game are we playing? End-to-end learning in normal and extensive form games
| Title | What game are we playing? End-to-end learning in normal and extensive form games |
| Authors | Chun Kai Ling, Fei Fang, J. Zico Kolter |
| Abstract | Although recent work in AI has made great progress in solving large, zero-sum, extensive-form games, the underlying assumption in most past work is that the parameters of the game itself are known to the agents. This paper deals with the relatively under-explored but equally important “inverse” setting, where the parameters of the underlying game are not known to all agents, but must be learned through observations. We propose a differentiable, end-to-end learning framework for addressing this task. In particular, we consider a regularized version of the game, equivalent to a particular form of quantal response equilibrium, and develop 1) a primal-dual Newton method for finding such equilibrium points in both normal and extensive form games; and 2) a backpropagation method that lets us analytically compute gradients of all relevant game parameters through the solution itself. This ultimately lets us learn the game by training in an end-to-end fashion, effectively by integrating a “differentiable game solver” into the loop of larger deep network architectures. We demonstrate the effectiveness of the learning method in several settings including poker and security game tasks. |
| Tasks | |
| Published | 2018-05-07 |
| URL | http://arxiv.org/abs/1805.02777v2 |
| http://arxiv.org/pdf/1805.02777v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-game-are-we-playing-end-to-end-learning |
| Repo | |
| Framework | |
Non-Local Graph-Based Prediction For Reversible Data Hiding In Images
| Title | Non-Local Graph-Based Prediction For Reversible Data Hiding In Images |
| Authors | Qi Chang, Gene Cheung, Yao Zhao, Xiaolong Li, Rongrong Ni |
| Abstract | Reversible data hiding (RDH) is desirable in applications where both the hidden message and the cover medium need to be recovered without loss. Among many RDH approaches is prediction-error expansion (PEE), containing two steps: i) prediction of a target pixel value, and ii) embedding according to the value of prediction-error. In general, higher prediction performance leads to larger embedding capacity and/or lower signal distortion. Leveraging on recent advances in graph signal processing (GSP), we pose pixel prediction as a graph-signal restoration problem, where the appropriate edge weights of the underlying graph are computed using a similar patch searched in a semi-local neighborhood. Specifically, for each candidate patch, we first examine eigenvalues of its structure tensor to estimate its local smoothness. If sufficiently smooth, we pose a maximum a posteriori (MAP) problem using either a quadratic Laplacian regularizer or a graph total variation (GTV) term as signal prior. While the MAP problem using the first prior has a closed-form solution, we design an efficient algorithm for the second prior using alternating direction method of multipliers (ADMM) with nested proximal gradient descent. Experimental results show that with better quality GSP-based prediction, at low capacity the visual quality of the embedded image exceeds state-of-the-art methods noticeably. |
| Tasks | |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.06935v1 |
| http://arxiv.org/pdf/1802.06935v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-local-graph-based-prediction-for |
| Repo | |
| Framework | |
