Paper Group ANR 1389
Incremental Bounded Model Checking of Artificial Neural Networks in CUDA. Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model. Active Learning for Binary Classification with Abstention. HyperGAN: A Generative Model for Diverse, Performant Neural Networks. Multi-Objective Optimisation of Damper Placement …
Incremental Bounded Model Checking of Artificial Neural Networks in CUDA
| Title | Incremental Bounded Model Checking of Artificial Neural Networks in CUDA |
| Authors | Luiz H. Sena, Iury V. Bessa, Mikhail R. Gadelha, Lucas C. Cordeiro, Edjard Mota |
| Abstract | Artificial Neural networks (ANNs) are powerful computing systems employed for various applications due to their versatility to generalize and to respond to unexpected inputs/patterns. However, implementations of ANNs for safety-critical systems might lead to failures, which are hardly predicted in the design phase since ANNs are highly parallel and their parameters are hardly interpretable. Here we develop and evaluate a novel symbolic software verification framework based on incremental bounded model checking (BMC) to check for adversarial cases and coverage methods in multi-layer perceptron (MLP). In particular, we further develop the efficient SMT-based Context-Bounded Model Checker for Graphical Processing Units (ESBMC-GPU) in order to ensure the reliability of certain safety properties in which safety-critical systems can fail and make incorrect decisions, thereby leading to unwanted material damage or even put lives in danger. This paper marks the first symbolic verification framework to reason over ANNs implemented in CUDA. Our experimental results show that our approach implemented in ESBMC-GPU can successfully verify safety properties and covering methods in ANNs and correctly generate 28 adversarial cases in MLPs. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12933v1 |
| https://arxiv.org/pdf/1907.12933v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-bounded-model-checking-of |
| Repo | |
| Framework | |
Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model
| Title | Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model |
| Authors | Likang Wu, Zhi Li, Hongke Zhao, Zhen Pan, Qi Liu, Enhong Chen |
| Abstract | Well begun is half done. In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms. However, estimating the early fundraising performance before the project published is very challenging and still under-explored. To that end, in this paper, we present a focused study on this important problem in a market modeling view. Specifically, we propose a Graph-based Market Environment model (GME) for estimating the early fundraising performance of the target project by exploiting the market environment. In addition, we discriminatively model the market competition and market evolution by designing two graph-based neural network architectures and incorporating them into the joint optimization stage. Finally, we conduct extensive experiments on the real-world crowdfunding data collected from Indiegogo.com. The experimental results clearly demonstrate the effectiveness of our proposed model for modeling and estimating the early fundraising performance of the target project. |
| Tasks | |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.06767v1 |
| https://arxiv.org/pdf/1912.06767v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-early-fundraising-performance-of |
| Repo | |
| Framework | |
Active Learning for Binary Classification with Abstention
| Title | Active Learning for Binary Classification with Abstention |
| Authors | Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi |
| Abstract | We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two variants of \emph{bounded-rate} abstention, and for each of them propose an active learning algorithm. All the proposed algorithms can work in the most commonly used active learning models, i.e., \emph{membership-query}, \emph{pool-based}, and \emph{stream-based} sampling. We obtain upper-bounds on the excess risk of our algorithms in a general non-parametric framework and establish their minimax near-optimality by deriving matching lower-bounds. Since our algorithms rely on the knowledge of some smoothness parameters of the regression function, we then describe a new strategy to adapt to these unknown parameters in a data-driven manner. Since the worst case computational complexity of our proposed algorithms increases exponentially with the dimension of the input space, we conclude the paper with a computationally efficient variant of our algorithm whose computational complexity has a polynomial dependence over a smaller but rich class of learning problems. |
| Tasks | Active Learning |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00303v1 |
| https://arxiv.org/pdf/1906.00303v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600303 |
| Repo | |
| Framework | |
HyperGAN: A Generative Model for Diverse, Performant Neural Networks
| Title | HyperGAN: A Generative Model for Diverse, Performant Neural Networks |
| Authors | Neale Ratzlaff, Li Fuxin |
| Abstract | Standard neural networks are often overconfident when presented with data outside the training distribution. We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters. HyperGAN does not require restrictive assumptions on priors, and networks sampled from it can be used to quickly create very large and diverse ensembles. HyperGAN employs a novel mixer to project prior samples to a latent space with correlated dimensions, and samples from the latent space are then used to generate weights for each layer of a deep neural network. We show that HyperGAN can learn to generate parameters which label the MNIST and CIFAR-10 datasets with competitive performance to fully supervised learning, while learning a rich distribution of effective parameters. We also show that HyperGAN can also provide better uncertainty estimates than standard ensembles by evaluating on out of distribution data as well as adversarial examples. |
| Tasks | |
| Published | 2019-01-30 |
| URL | https://arxiv.org/abs/1901.11058v2 |
| https://arxiv.org/pdf/1901.11058v2.pdf | |
| PWC | https://paperswithcode.com/paper/hypergan-a-generative-model-for-diverse |
| Repo | |
| Framework | |
Multi-Objective Optimisation of Damper Placement for Improved Seismic Response in Dynamically Similar Adjacent Buildings
| Title | Multi-Objective Optimisation of Damper Placement for Improved Seismic Response in Dynamically Similar Adjacent Buildings |
| Authors | Mahesh B. Patil, Ramakrishna U., Mohan S. C |
| Abstract | Multi-objective optimisation of damper placement in dynamically symmetric adjacent buildings is considered with identical viscoelastic dampers used for vibration control. First, exhaustive search is used to describe the solution space in terms of various quantities of interest such as maximum top floor displacement, maximum floor acceleration, base shear, and interstorey drift. With the help of examples, it is pointed out that the Pareto fronts in these problems contain a very small number of solutions. The effectiveness of two commonly used multi-objective evolutionary algorithms, viz., NSGA-II and MOPSO, is evaluated for a specific example. |
| Tasks | |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.03237v1 |
| https://arxiv.org/pdf/2001.03237v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-optimisation-of-damper |
| Repo | |
| Framework | |
Learning Affective Correspondence between Music and Image
| Title | Learning Affective Correspondence between Music and Image |
| Authors | Gaurav Verma, Eeshan Gunesh Dhekane, Tanaya Guha |
| Abstract | We introduce the problem of learning affective correspondence between audio (music) and visual data (images). For this task, a music clip and an image are considered similar (having true correspondence) if they have similar emotion content. In order to estimate this crossmodal, emotion-centric similarity, we propose a deep neural network architecture that learns to project the data from the two modalities to a common representation space, and performs a binary classification task of predicting the affective correspondence (true or false). To facilitate the current study, we construct a large scale database containing more than $3,500$ music clips and $85,000$ images with three emotion classes (positive, neutral, negative). The proposed approach achieves $61.67%$ accuracy for the affective correspondence prediction task on this database, outperforming two relevant and competitive baselines. We also demonstrate that our network learns modality-specific representations of emotion (without explicitly being trained with emotion labels), which are useful for emotion recognition in individual modalities. |
| Tasks | Emotion Recognition |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00150v2 |
| http://arxiv.org/pdf/1904.00150v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-affective-correspondence-between |
| Repo | |
| Framework | |
Embedded hyper-parameter tuning by Simulated Annealing
| Title | Embedded hyper-parameter tuning by Simulated Annealing |
| Authors | Matteo Fischetti, Matteo Stringher |
| Abstract | We propose a new metaheuristic training scheme that combines Stochastic Gradient Descent (SGD) and Discrete Optimization in an unconventional way. Our idea is to define a discrete neighborhood of the current SGD point containing a number of “potentially good moves” that exploit gradient information, and to search this neighborhood by using a classical metaheuristic scheme borrowed from Discrete Optimization. In the present paper we investigate the use of a simple Simulated Annealing (SA) metaheuristic that accepts/rejects a candidate new solution in the neighborhood with a probability that depends both on the new solution quality and on a parameter (the temperature) which is modified over time to lower the probability of accepting worsening moves. We use this scheme as an automatic way to perform hyper-parameter tuning, hence the title of the paper. A distinctive feature of our scheme is that hyper-parameters are modified within a single SGD execution (and not in an external loop, as customary) and evaluated on the fly on the current minibatch, i.e., their tuning is fully embedded within the SGD algorithm. The use of SA for training is not new, but previous proposals were mainly intended for non-differentiable objective functions for which SGD is not applied due to the lack of gradients. On the contrary, our SA method requires differentiability of (a proxy of) the loss function, and leverages on the availability of a gradient direction to define local moves that have a large probability to improve the current solution. Computational results on image classification (CIFAR-10) are reported, showing that the proposed approach leads to an improvement of the final validation accuracy for modern Deep Neural Networks such as ResNet34 and VGG16. |
| Tasks | Image Classification |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01504v1 |
| https://arxiv.org/pdf/1906.01504v1.pdf | |
| PWC | https://paperswithcode.com/paper/embedded-hyper-parameter-tuning-by-simulated |
| Repo | |
| Framework | |
Improving Skin Condition Classification with a Visual Symptom Checker Trained using Reinforcement Learning
| Title | Improving Skin Condition Classification with a Visual Symptom Checker Trained using Reinforcement Learning |
| Authors | Mohamed Akrout, Amir-massoud Farahmand, Tory Jarmain, Latif Abid |
| Abstract | We present a visual symptom checker that combines a pre-trained Convolutional Neural Network (CNN) with a Reinforcement Learning (RL) agent as a Question Answering (QA) model. This method increases the classification confidence and accuracy of the visual symptom checker, and decreases the average number of questions asked to narrow down the differential diagnosis. A Deep Q-Network (DQN)-based RL agent learns how to ask the patient about the presence of symptoms in order to maximize the probability of correctly identifying the underlying condition. The RL agent uses the visual information provided by CNN in addition to the answers to the asked questions to guide the QA system. We demonstrate that the RL-based approach increases the accuracy more than 20% compared to the CNN-only approach, which only uses the visual information to predict the condition. Moreover, the increased accuracy is up to 10% compared to the approach that uses the visual information provided by CNN along with a conventional decision tree-based QA system. We finally show that the RL-based approach not only outperforms the decision tree-based approach, but also narrows down the diagnosis faster in terms of the average number of asked questions. |
| Tasks | Question Answering |
| Published | 2019-03-08 |
| URL | https://arxiv.org/abs/1903.03495v4 |
| https://arxiv.org/pdf/1903.03495v4.pdf | |
| PWC | https://paperswithcode.com/paper/improving-skin-condition-classification-with-1 |
| Repo | |
| Framework | |
Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
| Title | Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition |
| Authors | Piotr Żelasko, Jan Mizgajski, Mikołaj Morzy, Adrian Szymczak, Piotr Szymański, Łukasz Augustyniak, Yishay Carmiel |
| Abstract | In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition is a powerful technique for dialog flow management in turn-oriented, human-machine dialogs. This technique can also be very useful in the context of human-human dialogs, though it serves a different purpose of key insight extraction from conversations. We argue that currently available intent recognition techniques are not applicable to human-human dialogs due to the complex structure of turn-taking and various disfluencies encountered in spontaneous conversations, exacerbated by speech recognition errors and scarcity of domain-specific labeled data. Without efficient key insight extraction techniques, raw human-human dialog transcripts remain significantly unexploited. Our contribution consists of a novel FST for intent indexing and an algorithm for fuzzy intent search over the lattice - a compact graph encoding of ASR’s hypotheses. We also develop a pruning strategy to constrain the fuzziness of the FST index search. Extracted intents represent linguistic domain knowledge and help us improve (rescore) the original transcript. We compare our method with a baseline, which uses only the most likely transcript hypothesis (best path), and find an increase in the total number of recognized intents by 25%. |
| Tasks | Speech Recognition |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07888v1 |
| https://arxiv.org/pdf/1908.07888v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807888 |
| Repo | |
| Framework | |
Optimal Differentially Private ADMM for Distributed Machine Learning
| Title | Optimal Differentially Private ADMM for Distributed Machine Learning |
| Authors | Jiahao Ding, Yanmin Gong, Chi Zhang, Miao Pan, Zhu Han |
| Abstract | Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of designing distributed machine learning algorithm, whereby each agent computes over local datasets and exchanges computation results with its neighbor agents in an iterative procedure. There exists significant privacy leakage during this iterative process if the local data is sensitive. In this paper, we propose a differentially private ADMM algorithm (P-ADMM) to provide dynamic zero-concentrated differential privacy (dynamic zCDP), by inserting Gaussian noise with linearly decaying variance. We prove that P-ADMM has the same convergence rate compared to the non-private counterpart, i.e., $\mathcal{O}(1/K)$ with $K$ being the number of iterations and linear convergence for general convex and strongly convex problems while providing differentially private guarantee. Moreover, through our experiments performed on real-world datasets, we empirically show that P-ADMM has the best-known performance among the existing differentially private ADMM based algorithms. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.02094v2 |
| http://arxiv.org/pdf/1901.02094v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-differentially-private-admm-for |
| Repo | |
| Framework | |
Cooperative Beamforming with Predictive Relay Selection for Urban mmWave Communications
| Title | Cooperative Beamforming with Predictive Relay Selection for Urban mmWave Communications |
| Authors | Anastasios Dimas, Dionysios S. Kalogerias, Athina P. Petropulu |
| Abstract | While millimeter wave (mmWave) communications promise high data rates, their sensitivity to blockage and severe signal attenuation presents challenges in their deployment in urban settings. To overcome these effects, we consider a distributed cooperative beamforming system, which relies on static relays deployed in clusters with similar channel characteristics, and where, at every time instance, only one relay from each cluster is selected to participate in beamforming to the destination. To meet the quality-of-service guarantees of the network, a key prerequisite for beamforming is relay selection. However, as the channels change with time, relay selection becomes a resource demanding task. Indeed, estimation of channel state information for all candidate relays, essential for relay selection, is a process that takes up bandwidth, wastes power and introduces latency and interference in the network. We instead propose a unique, predictive scheme for resource efficient relay selection, which exploits the special propagation patterns of the mmWave medium, and can be executed distributively across clusters, and in parallel to optimal beamforming-based communication. The proposed predictive scheme efficiently exploits spatiotemporal channel correlations with current and past networkwide Received Signal Strength (RSS), the latter being invariant to relay cluster size, measured sequentially during the operation of the system. Our numerical results confirm that our proposed relay selection strategy outperforms any randomized selection policy that does not exploit channel correlations, whereas, at the same time, it performs very close to an ideal scheme that uses complete, cluster size dependent RSS, and offers significant savings in terms of channel estimation overhead, providing substantially better network utilization, especially in dense topologies, typical in mmWave networks. |
| Tasks | |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12616v1 |
| https://arxiv.org/pdf/1907.12616v1.pdf | |
| PWC | https://paperswithcode.com/paper/cooperative-beamforming-with-predictive-relay |
| Repo | |
| Framework | |
A Computational-Hermeneutic Approach for Conceptual Explicitation
| Title | A Computational-Hermeneutic Approach for Conceptual Explicitation |
| Authors | David Fuenmayor, Christoph Benzmüller |
| Abstract | We present a computer-supported approach for the logical analysis and conceptual explicitation of argumentative discourse. Computational hermeneutics harnesses recent progresses in automated reasoning for higher-order logics and aims at formalizing natural-language argumentative discourse using flexible combinations of expressive non-classical logics. In doing so, it allows us to render explicit the tacit conceptualizations implicit in argumentative discursive practices. Our approach operates on networks of structured arguments and is iterative and two-layered. At one layer we search for logically correct formalizations for each of the individual arguments. At the next layer we select among those correct formalizations the ones which honor the argument’s dialectic role, i.e. attacking or supporting other arguments as intended. We operate at these two layers in parallel and continuously rate sentences’ formalizations by using, primarily, inferential adequacy criteria. An interpretive, logical theory will thus gradually evolve. This theory is composed of meaning postulates serving as explications for concepts playing a role in the analyzed arguments. Such a recursive, iterative approach to interpretation does justice to the inherent circularity of understanding: the whole is understood compositionally on the basis of its parts, while each part is understood only in the context of the whole (hermeneutic circle). We summarily discuss previous work on exemplary applications of human-in-the-loop computational hermeneutics in metaphysical discourse. We also discuss some of the main challenges involved in fully-automating our approach. By sketching some design ideas and reviewing relevant technologies, we argue for the technological feasibility of a highly-automated computational hermeneutics. |
| Tasks | |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.06582v2 |
| https://arxiv.org/pdf/1906.06582v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-computational-hermeneutic-approach-for |
| Repo | |
| Framework | |
Exploiting Belief Bases for Building Rich Epistemic Structures
| Title | Exploiting Belief Bases for Building Rich Epistemic Structures |
| Authors | Emiliano Lorini |
| Abstract | We introduce a semantics for epistemic logic exploiting a belief base abstraction. Differently from existing Kripke-style semantics for epistemic logic in which the notions of possible world and epistemic alternative are primitive, in the proposed semantics they are non-primitive but are defined from the concept of belief base. We show that this semantics allows us to define the universal epistemic model in a simpler and more compact way than existing inductive constructions of it. We provide (i) a number of semantic equivalence results for both the basic epistemic language with “individual belief” operators and its extension by the notion of “only believing”, and (ii) a lower bound complexity result for epistemic logic model checking relative to the universal epistemic model. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09114v1 |
| https://arxiv.org/pdf/1907.09114v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-belief-bases-for-building-rich |
| Repo | |
| Framework | |
Training Neural Networks for Likelihood/Density Ratio Estimation
| Title | Training Neural Networks for Likelihood/Density Ratio Estimation |
| Authors | George V. Moustakides, Kalliopi Basioti |
| Abstract | Various problems in Engineering and Statistics require the computation of the likelihood ratio function of two probability densities. In classical approaches the two densities are assumed known or to belong to some known parametric family. In a data-driven version we replace this requirement with the availability of data sampled from the densities of interest. For most well known problems in Detection and Hypothesis testing we develop solutions by providing neural network based estimates of the likelihood ratio or its transformations. This task necessitates the definition of proper optimizations which can be used for the training of the network. The main purpose of this work is to offer a simple and unified methodology for defining such optimization problems with guarantees that the solution is indeed the desired function. Our results are extended to cover estimates for likelihood ratios of conditional densities and estimates for statistics encountered in local approaches. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00405v2 |
| https://arxiv.org/pdf/1911.00405v2.pdf | |
| PWC | https://paperswithcode.com/paper/training-neural-networks-for |
| Repo | |
| Framework | |
GM-PLL: Graph Matching based Partial Label Learning
| Title | GM-PLL: Graph Matching based Partial Label Learning |
| Authors | Gengyu Lyu, Songhe Feng, Tao Wang, Congyan Lang, Yidong Li |
| Abstract | Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct. The key to deal with such problem is to disambiguate the candidate label sets and obtain the correct assignments between instances and their candidate labels. In this paper, we interpret such assignments as instance-to-label matchings, and reformulate the task of PLL as a matching selection problem. To model such problem, we propose a novel Graph Matching based Partial Label Learning (GM-PLL) framework, where Graph Matching (GM) scheme is incorporated owing to its excellent capability of exploiting the instance and label relationship. Meanwhile, since conventional one-to-one GM algorithm does not satisfy the constraint of PLL problem that multiple instances may correspond to the same label, we extend a traditional one-to-one probabilistic matching algorithm to the many-to-one constraint, and make the proposed framework accommodate to the PLL problem. Moreover, we also propose a relaxed matching prediction model, which can improve the prediction accuracy via GM strategy. Extensive experiments on both artificial and real-world data sets demonstrate that the proposed method can achieve superior or comparable performance against the state-of-the-art methods. |
| Tasks | Graph Matching |
| Published | 2019-01-10 |
| URL | http://arxiv.org/abs/1901.03073v1 |
| http://arxiv.org/pdf/1901.03073v1.pdf | |
| PWC | https://paperswithcode.com/paper/gm-pll-graph-matching-based-partial-label |
| Repo | |
| Framework | |
