Paper Group ANR 604
Objective Assessment of Social Skills Using Automated Language Analysis for Identification of Schizophrenia and Bipolar Disorder. Abstract Argumentation and the Rational Man. Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates. Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning …
Objective Assessment of Social Skills Using Automated Language Analysis for Identification of Schizophrenia and Bipolar Disorder
| Title | Objective Assessment of Social Skills Using Automated Language Analysis for Identification of Schizophrenia and Bipolar Disorder |
| Authors | Rohit Voleti, Stephanie Woolridge, Julie M. Liss, Melissa Milanovic, Christopher R. Bowie, Visar Berisha |
| Abstract | Several studies have shown that speech and language features, automatically extracted from clinical interviews or spontaneous discourse, have diagnostic value for mental disorders such as schizophrenia and bipolar disorder. They typically make use of a large feature set to train a classifier for distinguishing between two groups of interest, i.e. a clinical and control group. However, a purely data-driven approach runs the risk of overfitting to a particular data set, especially when sample sizes are limited. Here, we first down-select the set of language features to a small subset that is related to a well-validated test of functional ability, the Social Skills Performance Assessment (SSPA). This helps establish the concurrent validity of the selected features. We use only these features to train a simple classifier to distinguish between groups of interest. Linear regression reveals that a subset of language features can effectively model the SSPA, with a correlation coefficient of 0.75. Furthermore, the same feature set can be used to build a strong binary classifier to distinguish between healthy controls and a clinical group (AUC = 0.96) and also between patients within the clinical group with schizophrenia and bipolar I disorder (AUC = 0.83). |
| Tasks | |
| Published | 2019-04-24 |
| URL | https://arxiv.org/abs/1904.10622v2 |
| https://arxiv.org/pdf/1904.10622v2.pdf | |
| PWC | https://paperswithcode.com/paper/objective-assessment-of-social-skills-using |
| Repo | |
| Framework | |
Abstract Argumentation and the Rational Man
| Title | Abstract Argumentation and the Rational Man |
| Authors | Timotheus Kampik, Juan Carlos Nieves |
| Abstract | Abstract argumentation has emerged as a method for non-monotonic reasoning that has gained tremendous traction in the symbolic artificial intelligence community. In the literature, the different approaches to abstract argumentation that were refined over the years are typically evaluated from a logics perspective; an analysis that is based on models of ideal, rational decision-making does not exist. In this paper, we work towards addressing this issue by analyzing abstract argumentation from the perspective of the rational man paradigm in microeconomic theory. To assess under which conditions abstract argumentation-based decision-making can be considered economically rational, we derive reference independence as a non-monotonic inference property from a formal model of economic rationality and create a new argumentation principle that ensures compliance with these properties. We then compare the reference independence principle with other reasoning principles, in particular with cautious monotony and rational monotony. We show that the argumentation semantics as proposed in Dung’s classical paper, as well as other semantics we evaluate–with the exception of the SCC-recursive CF2 semantics–do not comply with the reference independence principle. Consequently, we investigate how structural properties of argumentation frameworks impact the reference independence principle, and identify cyclic expansions (both even and odd cycles) as the root of the problem. Finally, we put reference independence into the context of preference-based argumentation and show that for this argumentation variant, which explicitly models preferences, reference independence cannot be ensured in a straight-forward manner. |
| Tasks | Abstract Argumentation, Decision Making |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13024v3 |
| https://arxiv.org/pdf/1911.13024v3.pdf | |
| PWC | https://paperswithcode.com/paper/abstract-argumentation-and-the-rational-man |
| Repo | |
| Framework | |
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
| Title | Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates |
| Authors | Adil Salim, Dmitry Kovalev, Peter Richtárik |
| Abstract | We propose a new algorithm—Stochastic Proximal Langevin Algorithm (SPLA)—for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth term and multiple stochastic nonsmooth terms. In each iteration, our splitting technique only requires access to a stochastic gradient of the smooth term and a stochastic proximal operator for each of the nonsmooth terms. We establish nonasymptotic sublinear and linear convergence rates under convexity and strong convexity of the smooth term, respectively, expressed in terms of the KL divergence and Wasserstein distance. We illustrate the efficiency of our sampling technique through numerical simulations on a Bayesian learning task. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11768v1 |
| https://arxiv.org/pdf/1905.11768v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-proximal-langevin-algorithm |
| Repo | |
| Framework | |
Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
| Title | Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward |
| Authors | Adnan Qayyum, Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha |
| Abstract | Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation—which will be fuelled by concomitant advances in technologies for machine learning (ML) and wireless communications—will enable a future vehicular ecosystem that is better featured and more efficient. However, there are lurking security problems related to the use of ML in such a critical setting where an incorrect ML decision may not only be a nuisance but can lead to loss of precious lives. In this paper, we present an in-depth overview of the various challenges associated with the application of ML in vehicular networks. In addition, we formulate the ML pipeline of CAVs and present various potential security issues associated with the adoption of ML methods. In particular, we focus on the perspective of adversarial ML attacks on CAVs and outline a solution to defend against adversarial attacks in multiple settings. |
| Tasks | Autonomous Vehicles |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12762v1 |
| https://arxiv.org/pdf/1905.12762v1.pdf | |
| PWC | https://paperswithcode.com/paper/securing-connected-autonomous-vehicles |
| Repo | |
| Framework | |
Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
| Title | Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks |
| Authors | Yi Luo, Deniz Mengu, Nezih T. Yardimci, Yair Rivenson, Muhammed Veli, Mona Jarrahi, Aydogan Ozcan |
| Abstract | We report a broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally-incoherent broadband source to all-optically perform a specific task learned using deep learning. We experimentally validated the success of this broadband diffractive neural network architecture by designing, fabricating and testing seven different multi-layer, diffractive optical systems that transform the optical wavefront generated by a broadband THz pulse to realize (1) a series of tunable, single passband as well as dual passband spectral filters, and (2) spatially-controlled wavelength de-multiplexing. Merging the native or engineered dispersion of various material systems with a deep learning-based design strategy, broadband diffractive neural networks help us engineer light-matter interaction in 3D, diverging from intuitive and analytical design methods to create task-specific optical components that can all-optically perform deterministic tasks or statistical inference for optical machine learning. |
| Tasks | |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06553v1 |
| https://arxiv.org/pdf/1909.06553v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-of-task-specific-optical-systems-using |
| Repo | |
| Framework | |
Markerless Augmented Advertising for Sports Videos
| Title | Markerless Augmented Advertising for Sports Videos |
| Authors | Hallee E. Wong, Osman Akar, Emmanuel Antonio Cuevas, Iuliana Tabian, Divyaa Ravichandran, Iris Fu, Cambron Carter |
| Abstract | Markerless augmented reality can be a challenging computer vision task, especially in live broadcast settings and in the absence of information related to the video capture such as the intrinsic camera parameters. This typically requires the assistance of a skilled artist, along with the use of advanced video editing tools in a post-production environment. We present an automated video augmentation pipeline that identifies textures of interest and overlays an advertisement onto these regions. We constrain the advertisement to be placed in a way that is aesthetic and natural. The aim is to augment the scene such that there is no longer a need for commercial breaks. In order to achieve seamless integration of the advertisement with the original video we build a 3D representation of the scene, place the advertisement in 3D, and then project it back onto the image plane. After successful placement in a single frame, we use homography-based, shape-preserving tracking such that the advertisement appears perspective correct for the duration of a video clip. The tracker is designed to handle smooth camera motion and shot boundaries. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09394v1 |
| https://arxiv.org/pdf/1907.09394v1.pdf | |
| PWC | https://paperswithcode.com/paper/markerless-augmented-advertising-for-sports |
| Repo | |
| Framework | |
Performance Effectiveness of Multimedia Information Search Using the Epsilon-Greedy Algorithm
| Title | Performance Effectiveness of Multimedia Information Search Using the Epsilon-Greedy Algorithm |
| Authors | Nikki Lijing Kuang, Clement H. C. Leung |
| Abstract | In the search and retrieval of multimedia objects, it is impractical to either manually or automatically extract the contents for indexing since most of the multimedia contents are not machine extractable, while manual extraction tends to be highly laborious and time-consuming. However, by systematically capturing and analyzing the feedback patterns of human users, vital information concerning the multimedia contents can be harvested for effective indexing and subsequent search. By learning from the human judgment and mental evaluation of users, effective search indices can be gradually developed and built up, and subsequently be exploited to find the most relevant multimedia objects. To avoid hovering around a local maximum, we apply the epsilon-greedy method to systematically explore the search space. Through such methodic exploration, we show that the proposed approach is able to guarantee that the most relevant objects can always be discovered, even though initially it may have been overlooked or not regarded as relevant. The search behavior of the present approach is quantitatively analyzed, and closed-form expressions are obtained for the performance of two variants of the epsilon-greedy algorithm, namely EGSE-A and EGSE-B. Simulations and experiments on real data set have been performed which show good agreement with the theoretical findings. The present method is able to leverage exploration in an effective way to significantly raise the performance of multimedia information search, and enables the certain discovery of relevant objects which may be otherwise undiscoverable. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09891v1 |
| https://arxiv.org/pdf/1911.09891v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-effectiveness-of-multimedia |
| Repo | |
| Framework | |
Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning
| Title | Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning |
| Authors | Xiangxi Mo, Ruizhe Cheng, Tianyi Fang |
| Abstract | We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between training time and accuracy. By adding “attention module” to each convolutional filters of the pre-trained network, we are able to rank and adjust the importance of each convolutional signal in an end-to-end pipeline. In this report, we show our method can adapt a pre-trianed ResNet50 for a fine-grained transfer learning task within few epochs and achieve accuracy above conventional transfer learning methods and close to models trained from scratch. Our model also offer interpretable result because the rank of the convolutional signal shows which convolution channels are utilized and amplified to achieve better classification result, as well as which signal should be treated as noise for the specific transfer learning task, which could be pruned to lower model size. |
| Tasks | Fine-Grained Image Classification, Image Classification, Transfer Learning |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.04950v1 |
| https://arxiv.org/pdf/1906.04950v1.pdf | |
| PWC | https://paperswithcode.com/paper/pay-attention-to-convolution-filters-towards |
| Repo | |
| Framework | |
Center of circle after perspective transformation
| Title | Center of circle after perspective transformation |
| Authors | Xi Wang, Albert Chern, Marc Alexa |
| Abstract | Video-based glint-free eye tracking commonly estimates gaze direction based on the pupil center. The boundary of the pupil is fitted with an ellipse and the euclidean center of the ellipse in the image is taken as the center of the pupil. However, the center of the pupil is generally not mapped to the center of the ellipse by the projective camera transformation. This error resulting from using a point that is not the true center of the pupil directly affects eye tracking accuracy. We investigate the underlying geometric problem of determining the center of a circular object based on its projective image. The main idea is to exploit two concentric circles – in the application scenario these are the pupil and the iris. We show that it is possible to computed the center and the ratio of the radii from the mapped concentric circles with a direct method that is fast and robust in practice. We evaluate our method on synthetically generated data and find that it improves systematically over using the center of the fitted ellipse. Apart from applications of eye tracking we estimate that our approach will be useful in other tracking applications. |
| Tasks | Eye Tracking |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04541v1 |
| http://arxiv.org/pdf/1902.04541v1.pdf | |
| PWC | https://paperswithcode.com/paper/center-of-circle-after-perspective |
| Repo | |
| Framework | |
Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
| Title | Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks |
| Authors | Yihui He, Jianing Qian, Jianren Wang |
| Abstract | Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%. |
| Tasks | Self-Driving Cars |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09455v1 |
| https://arxiv.org/pdf/1910.09455v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-wise-decomposition-for-accelerating |
| Repo | |
| Framework | |
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations
| Title | Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations |
| Authors | Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, Tom Diethe |
| Abstract | Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text perturbation using the notion of dx-privacy designed to achieve geo-indistinguishability in location data. Our approach applies carefully calibrated noise to vector representation of words in a high dimension space as defined by word embedding models. We present a privacy proof that satisfies dx-privacy where the privacy parameter epsilon provides guarantees with respect to a distance metric defined by the word embedding space. We demonstrate how epsilon can be selected by analyzing plausible deniability statistics backed up by large scale analysis on GloVe and fastText embeddings. We conduct privacy audit experiments against 2 baseline models and utility experiments on 3 datasets to demonstrate the tradeoff between privacy and utility for varying values of epsilon on different task types. Our results demonstrate practical utility (< 2% utility loss for training binary classifiers) while providing better privacy guarantees than baseline models. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08902v1 |
| https://arxiv.org/pdf/1910.08902v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-and-utility-preserving-textual |
| Repo | |
| Framework | |
Deep Latent Defence
| Title | Deep Latent Defence |
| Authors | Giulio Zizzo, Chris Hankin, Sergio Maffeis, Kevin Jones |
| Abstract | Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to cause misclassification. The level of perturbation an attacker needs to introduce in order to cause such a misclassification can be extremely small, and often imperceptible. This is of significant security concern, particularly where misclassification can cause harm to humans. We thus propose Deep Latent Defence, an architecture which seeks to combine adversarial training with a detection system. At its core Deep Latent Defence has a adversarially trained neural network. A series of encoders take the intermediate layer representation of data as it passes though the network and project it to a latent space which we use for detecting adversarial samples via a $k$-nn classifier. We present results using both grey and white box attackers, as well as an adaptive $L_{\infty}$ bounded attack which was constructed specifically to try and evade our defence. We find that even under the strongest attacker model that we have investigated our defence is able to offer significant defensive benefits. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03916v1 |
| https://arxiv.org/pdf/1910.03916v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-latent-defence |
| Repo | |
| Framework | |
Batch Tournament Selection for Genetic Programming
| Title | Batch Tournament Selection for Genetic Programming |
| Authors | Vinicius V. Melo, Danilo Vasconcellos Vargas, Wolfgang Banzhaf |
| Abstract | Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude faster than lexicase selection while achieving a competitive quality of solutions. Tests on a number of regression datasets show that BTS compares well with lexicase selection in terms of mean absolute error while having a speed-up of up to 25 times. Surprisingly, BTS and lexicase selection have almost no difference in both diversity and performance. This reveals that batches and ordered test cases are completely different mechanisms which share the same general principle fostering the specialization of individuals. This work introduces an efficient algorithm that sheds light onto the main principles behind the success of lexicase, potentially opening up a new range of possibilities for algorithms to come. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08658v1 |
| http://arxiv.org/pdf/1904.08658v1.pdf | |
| PWC | https://paperswithcode.com/paper/batch-tournament-selection-for-genetic |
| Repo | |
| Framework | |
Optimal Control of Complex Systems through Variational Inference with a Discrete Event Decision Process
| Title | Optimal Control of Complex Systems through Variational Inference with a Discrete Event Decision Process |
| Authors | Wen Dong, Bo Liu, Fan Yang |
| Abstract | Complex social systems are composed of interconnected individuals whose interactions result in group behaviors. Optimal control of a real-world complex system has many applications, including road traffic management, epidemic prevention, and information dissemination. However, such real-world complex system control is difficult to achieve because of high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decision maker. Prior methods can be divided into two categories: simulation-based and analytical approaches. Existing simulation approaches have high-variance in Monte Carlo integration, and the analytical approaches suffer from modeling inaccuracy. We adopted simulation modeling in specifying the complex dynamics of a complex system, and developed analytical solutions for searching optimal strategies in a complex network with high-dimensional state-action space. To capture the complex system dynamics, we formulate the complex social network decision making problem as a discrete event decision process. To address the curse of dimensionality and search in high-dimensional state action spaces in complex systems, we reduce control of a complex system to variational inference and parameter learning, introduce Bethe entropy approximation, and develop an expectation propagation algorithm. Our proposed algorithm leads to higher system expected rewards, faster convergence, and lower variance of value function in a real-world transportation scenario than state-of-the-art analytical and sampling approaches. |
| Tasks | Decision Making |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02606v1 |
| https://arxiv.org/pdf/1905.02606v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-control-of-complex-systems-through |
| Repo | |
| Framework | |
Generative Temporal Link Prediction via Self-tokenized Sequence Modeling
| Title | Generative Temporal Link Prediction via Self-tokenized Sequence Modeling |
| Authors | Yue Wang, Chenwei Zhang, Shen Wang, Philip S. Yu, Lu Bai, Lixin Cui, Guandong Xu |
| Abstract | We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link formation patterns from the observed links with a sequence modeling framework and has the ability to generate the emerging links by inferring from the probability distribution on the potential future links. To avoid overfitting caused by treating each link as a unique token, we propose a self-tokenization mechanism to transform each raw link in the network to an abstract aggregation token automatically. The self-tokenization is seamlessly integrated into the sequence modeling framework, which allows the proposed GLSM model to have the generalization capability to discover link formation patterns beyond raw link sequences. We compare GLSM with the existing state-of-art methods on five real-world datasets. The experimental results demonstrate that GLSM obtains future positive links effectively in a generative fashion while achieving the best performance (2-10% improvements on AUC) among other alternatives. |
| Tasks | Link Prediction, Tokenization |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11486v1 |
| https://arxiv.org/pdf/1911.11486v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-temporal-link-prediction-via-self |
| Repo | |
| Framework | |
