Paper Group ANR 83
Semantic Preserving Generative Adversarial Models. Transforming the output of GANs by fine-tuning them with features from different datasets. Object-centric Forward Modeling for Model Predictive Control. Learning To Characterize Adversarial Subspaces. Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games. Differentially P …
Semantic Preserving Generative Adversarial Models
| Title | Semantic Preserving Generative Adversarial Models |
| Authors | Shahar Harel, Meir Maor, Amir Ronen |
| Abstract | We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and generated data differ over a controlled semantic space. We demonstrate that such models have the ability to generate objects with strong guarantees on their properties in a wide range of domains. They require less data than ordinary GANs, provide natural stopping conditions, uncover important properties of the data, and enhance transfer learning. Our techniques can be combined with standard generative models. We demonstrate the usefulness of our approach by applying it to several unrelated domains: generating good locations for cellular antennae, molecule generation preserving key chemical properties, and generating and extrapolating lines from very few data points. Intriguing open problems are presented as well. |
| Tasks | Transfer Learning |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02804v1 |
| https://arxiv.org/pdf/1910.02804v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-preserving-generative-adversarial |
| Repo | |
| Framework | |
Transforming the output of GANs by fine-tuning them with features from different datasets
| Title | Transforming the output of GANs by fine-tuning them with features from different datasets |
| Authors | Terence Broad, Mick Grierson |
| Abstract | In this work we present a method for fine-tuning pre-trained GANs with features from different datasets, resulting in the transformation of the output distribution into a new distribution with novel characteristics. The weights of the generator are updated using the weighted sum of the losses from a cross-dataset classifier and the frozen weights of the pre-trained discriminator. We discuss details of the technical implementation and share some of the visual results from this training process. |
| Tasks | |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02411v1 |
| https://arxiv.org/pdf/1910.02411v1.pdf | |
| PWC | https://paperswithcode.com/paper/transforming-the-output-of-gans-by-fine |
| Repo | |
| Framework | |
Object-centric Forward Modeling for Model Predictive Control
| Title | Object-centric Forward Modeling for Model Predictive Control |
| Authors | Yufei Ye, Dhiraj Gandhi, Abhinav Gupta, Shubham Tulsiani |
| Abstract | We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. We propose to model a scene as a collection of objects, each with an explicit spatial location and implicit visual feature, and learn to model the effects of actions using random interaction data. Our model allows capturing the robot-object and object-object interactions, and leads to more sample-efficient and accurate predictions. We show that this learned model can be leveraged to search for action sequences that lead to desired goal configurations, and that in conjunction with a learned correction module, this allows for robust closed loop execution. We present experiments both in simulation and the real world, and show that our approach improves over alternate implicit or pixel-space forward models. Please see our project page (https://judyye.github.io/ocmpc/) for result videos. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03568v1 |
| https://arxiv.org/pdf/1910.03568v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-centric-forward-modeling-for-model |
| Repo | |
| Framework | |
Learning To Characterize Adversarial Subspaces
| Title | Learning To Characterize Adversarial Subspaces |
| Authors | Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Yuan He, Hui Xue |
| Abstract | Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of \textit{adversarial subspaces} where adversarial examples lie. However, we find these methods are not working in practical attack detection scenarios. Because the artificially defined features are lack of robustness and show limitation in discriminative power to detect strong attacks. To solve this problem, we propose a novel adversarial detection method which identifies adversaries by adaptively learning reasonable metrics to characterize adversarial subspaces. As auxiliary context information, \textit{k} nearest neighbors are used to represent the surrounded subspace of the detected sample. We propose an innovative model called Neighbor Context Encoder (NCE) to learn from \textit{k} neighbors context and infer if the detected sample is normal or adversarial. We conduct thorough experiment on CIFAR-10, CIFAR-100 and ImageNet dataset. The results demonstrate that our approach surpasses all existing methods under three settings: \textit{attack-aware black-box detection}, \textit{attack-unaware black-box detection} and \textit{white-box detection}. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06587v1 |
| https://arxiv.org/pdf/1911.06587v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-characterize-adversarial |
| Repo | |
| Framework | |
Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games
| Title | Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games |
| Authors | Xinliang Song, Tonghan Wang, Chongjie Zhang |
| Abstract | Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees. To address this challenge, this paper presents a new gradient-based learning algorithm, called Gradient Ascent with Shrinking Policy Prediction (GA-SPP), which augments the basic gradient ascent approach with the concept of shrinking policy prediction. The key idea behind this algorithm is that an agent adjusts its strategy in response to the forecasted strategy of the other agent, instead of its current one. GA-SPP is shown formally to have Nash convergence in larger settings than existing gradient-based multi-agent learning methods. Furthermore, unlike existing gradient-based methods, GA-SPP’s theoretical guarantees do not assume the learning rate to be infinitesimal. |
| Tasks | |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02868v1 |
| http://arxiv.org/pdf/1903.02868v1.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-of-multi-agent-learning-with-a |
| Repo | |
| Framework | |
Differentially Private Precision Matrix Estimation
| Title | Differentially Private Precision Matrix Estimation |
| Authors | Wenqing Su, Xiao Guo, Hai Zhang |
| Abstract | In this paper, we study the problem of precision matrix estimation when the dataset contains sensitive information. In the differential privacy framework, we develop a differentially private ridge estimator by perturbing the sample covariance matrix. Then we develop a differentially private graphical lasso estimator by using the alternating direction method of multipliers (ADMM) algorithm. The theoretical results and empirical results that show the utility of the proposed methods are also provided. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02750v1 |
| https://arxiv.org/pdf/1909.02750v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-precision-matrix |
| Repo | |
| Framework | |
Extracting information from free text through unsupervised graph-based clustering: an application to patient incident records
| Title | Extracting information from free text through unsupervised graph-based clustering: an application to patient incident records |
| Authors | M. Tarik Altuncu, Eloise Sorin, Joshua D. Symons, Erik Mayer, Sophia N. Yaliraki, Francesca Toni, Mauricio Barahona |
| Abstract | The large volume of text in electronic healthcare records often remains underused due to a lack of methodologies to extract interpretable content. Here we present an unsupervised framework for the analysis of free text that combines text-embedding with paragraph vectors and graph-theoretical multiscale community detection. We analyse text from a corpus of patient incident reports from the National Health Service in England to find content-based clusters of reports in an unsupervised manner and at different levels of resolution. Our unsupervised method extracts groups with high intrinsic textual consistency and compares well against categories hand-coded by healthcare personnel. We also show how to use our content-driven clusters to improve the supervised prediction of the degree of harm of the incident based on the text of the report. Finally, we discuss future directions to monitor reports over time, and to detect emerging trends outside pre-existing categories. |
| Tasks | Community Detection |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.00183v1 |
| https://arxiv.org/pdf/1909.00183v1.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-information-from-free-text-through |
| Repo | |
| Framework | |
Robust End-to-End Speaker Verification Using EEG
| Title | Robust End-to-End Speaker Verification Using EEG |
| Authors | Yan Han, Gautam Krishna, Co Tran, Mason Carnahan, Ahmed H Tewfik |
| Abstract | In this paper we demonstrate that performance of a speaker verification system can be improved by concatenating electroencephalography (EEG) signal features with speech signal. We use state of art end to end deep learning model for performing speaker verification and we demonstrate our results for noisy speech. Our results indicate that EEG signals can improve the robustness of speaker verification systems. |
| Tasks | EEG, Speaker Verification |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.08044v4 |
| https://arxiv.org/pdf/1906.08044v4.pdf | |
| PWC | https://paperswithcode.com/paper/robust-end-to-end-speaker-verification-using |
| Repo | |
| Framework | |
Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks
| Title | Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks |
| Authors | Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao, Christos Faloutsos |
| Abstract | How can we estimate the importance of nodes in a knowledge graph (KG)? A KG is a multi-relational graph that has proven valuable for many tasks including question answering and semantic search. In this paper, we present GENI, a method for tackling the problem of estimating node importance in KGs, which enables several downstream applications such as item recommendation and resource allocation. While a number of approaches have been developed to address this problem for general graphs, they do not fully utilize information available in KGs, or lack flexibility needed to model complex relationship between entities and their importance. To address these limitations, we explore supervised machine learning algorithms. In particular, building upon recent advancement of graph neural networks (GNNs), we develop GENI, a GNN-based method designed to deal with distinctive challenges involved with predicting node importance in KGs. Our method performs an aggregation of importance scores instead of aggregating node embeddings via predicate-aware attention mechanism and flexible centrality adjustment. In our evaluation of GENI and existing methods on predicting node importance in real-world KGs with different characteristics, GENI achieves 5-17% higher NDCG@100 than the state of the art. |
| Tasks | Knowledge Graphs, Question Answering |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08865v2 |
| https://arxiv.org/pdf/1905.08865v2.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-node-importance-in-knowledge |
| Repo | |
| Framework | |
Tiresias: Predicting Security Events Through Deep Learning
| Title | Tiresias: Predicting Security Events Through Deep Learning |
| Authors | Yun Shen, Enrico Mariconti, Pierre-Antoine Vervier, Gianluca Stringhini |
| Abstract | With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps that will be taken by an adversary when performing an attack. However this is still an open research problem, and previous research in predicting malicious events only looked at binary outcomes (e.g., whether an attack would happen or not), but not at the specific steps that an attacker would undertake. To fill this gap we present Tiresias, a system that leverages Recurrent Neural Networks (RNNs) to predict future events on a machine, based on previous observations. We test Tiresias on a dataset of 3.4 billion security events collected from a commercial intrusion prevention system, and show that our approach is effective in predicting the next event that will occur on a machine with a precision of up to 0.93. We also show that the models learned by Tiresias are reasonably stable over time, and provide a mechanism that can identify sudden drops in precision and trigger a retraining of the system. Finally, we show that the long-term memory typical of RNNs is key in performing event prediction, rendering simpler methods not up to the task. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10328v1 |
| https://arxiv.org/pdf/1905.10328v1.pdf | |
| PWC | https://paperswithcode.com/paper/tiresias-predicting-security-events-through |
| Repo | |
| Framework | |
Explaining black box decisions by Shapley cohort refinement
| Title | Explaining black box decisions by Shapley cohort refinement |
| Authors | Masayoshi Mase, Art B. Owen, Benjamin Seiler |
| Abstract | We introduce a variable importance measure to explain the importance of individual variables to a decision made by a black box function. Our measure is based on the Shapley value from cooperative game theory. Measures of variable importance usually work by changing the value of one or more variables with the others held fixed and then recomputing the function of interest. That approach is problematic because it can create very unrealistic combinations of predictors that never appear in practice or that were never present when the prediction function was being created. Our cohort refinement Shapley approach measures variable importance without using any data points that were not actually observed. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00467v1 |
| https://arxiv.org/pdf/1911.00467v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-black-box-decisions-by-shapley |
| Repo | |
| Framework | |
Accurate and Compact Convolutional Neural Networks with Trained Binarization
| Title | Accurate and Compact Convolutional Neural Networks with Trained Binarization |
| Authors | Zhe Xu, Ray C. C. Cheung |
| Abstract | Although convolutional neural networks (CNNs) are now widely used in various computer vision applications, its huge resource demanding on parameter storage and computation makes the deployment on mobile and embedded devices difficult. Recently, binary convolutional neural networks are explored to help alleviate this issue by quantizing both weights and activations with only 1 single bit. However, there may exist a noticeable accuracy degradation when compared with full-precision models. In this paper, we propose an improved training approach towards compact binary CNNs with higher accuracy. Trainable scaling factors for both weights and activations are introduced to increase the value range. These scaling factors will be trained jointly with other parameters via backpropagation. Besides, a specific training algorithm is developed including tight approximation for derivative of discontinuous binarization function and $L_2$ regularization acting on weight scaling factors. With these improvements, the binary CNN achieves 92.3% accuracy on CIFAR-10 with VGG-Small network. On ImageNet, our method also obtains 46.1% top-1 accuracy with AlexNet and 54.2% with Resnet-18 surpassing previous works. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11366v1 |
| https://arxiv.org/pdf/1909.11366v1.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-and-compact-convolutional-neural |
| Repo | |
| Framework | |
FACE: Feasible and Actionable Counterfactual Explanations
| Title | FACE: Feasible and Actionable Counterfactual Explanations |
| Authors | Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez, Tijl De Bie, Peter Flach |
| Abstract | Work in Counterfactual Explanations tends to focus on the principle of “the closest possible world” that identifies small changes leading to the desired outcome. In this paper we argue that while this approach might initially seem intuitively appealing it exhibits shortcomings not addressed in the current literature. First, a counterfactual example generated by the state-of-the-art systems is not necessarily representative of the underlying data distribution, and may therefore prescribe unachievable goals(e.g., an unsuccessful life insurance applicant with severe disability may be advised to do more sports). Secondly, the counterfactuals may not be based on a “feasible path” between the current state of the subject and the suggested one, making actionable recourse infeasible (e.g., low-skilled unsuccessful mortgage applicants may be told to double their salary, which may be hard without first increasing their skill level). These two shortcomings may render counterfactual explanations impractical and sometimes outright offensive. To address these two major flaws, first of all, we propose a new line of Counterfactual Explanations research aimed at providing actionable and feasible paths to transform a selected instance into one that meets a certain goal. Secondly, we propose FACE: an algorithmically sound way of uncovering these “feasible paths” based on the shortest path distances defined via density-weighted metrics. Our approach generates counterfactuals that are coherent with the underlying data distribution and supported by the “feasible paths” of change, which are achievable and can be tailored to the problem at hand. |
| Tasks | |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09369v2 |
| https://arxiv.org/pdf/1909.09369v2.pdf | |
| PWC | https://paperswithcode.com/paper/face-feasible-and-actionable-counterfactual |
| Repo | |
| Framework | |
Global Semantic Description of Objects based on Prototype Theory
| Title | Global Semantic Description of Objects based on Prototype Theory |
| Authors | Omar Vidal Pino, Erickson Rangel Nascimento, Mario Fernando Montenegro Campos |
| Abstract | In this paper, we introduce a novel semantic description approach inspired on Prototype Theory foundations. We propose a Computational Prototype Model (CPM) that encodes and stores the central semantic meaning of objects category: the semantic prototype. Also, we introduce a Prototype-based Description Model that encodes the semantic meaning of an object while describing its features using our CPM model. Our description method uses semantic prototypes computed by CNN-classifications models to create discriminative signatures that describe an object highlighting its most distinctive features within the category. Our experiments show that: i) our CPM model (semantic prototype + distance metric) is able to describe the internal semantic structure of objects categories; ii) our semantic distance metric can be understood as the object visual typicality score within a category; iii) our descriptor encoding is semantically interpretable and significantly outperforms other image global encodings in clustering and classification tasks. |
| Tasks | |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03365v2 |
| https://arxiv.org/pdf/1906.03365v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-semantic-description-of-objects-based |
| Repo | |
| Framework | |
Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory
| Title | Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory |
| Authors | Ya Li, Xinyu Liu, Dan Liu, Xueqiang Zhang, Junhua Liu |
| Abstract | Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through lexcially-constrained beam search in the decoding phase. Unfortunately, these lexically-constrained beam search methods suffer two fatal disadvantages: high computational complexity and hard beam search which generates unexpected translations. In this paper, we propose to learn the ability of lexically-constrained translation with external memory, which can overcome the above mentioned disadvantages. For the training process, automatically extracted phrase pairs are extracted from alignment and sentence parsing, then further be encoded into an external memory. This memory is then used to provide lexically-constrained information for training through a memory-attention machanism. Various experiments are conducted on WMT Chinese to English and English to German tasks. All the results can demonstrate the effectiveness of our method. |
| Tasks | Machine Translation |
| Published | 2019-01-31 |
| URL | http://arxiv.org/abs/1901.11344v1 |
| http://arxiv.org/pdf/1901.11344v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-efficient-lexically-constrained |
| Repo | |
| Framework | |
