Paper Group AWR 1
Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series. One-shot Learning for Question-Answering in Gaokao History Challenge. Adversarial Clustering: A Grid Based Clustering Algorithm Against Active Adversaries. Real Time Bangladeshi Sign Language Detection using Faster R-CNN. One-Shot Learning of Multi-Step Tasks from …
Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
| Title | Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series |
| Authors | Dan Li, Dacheng Chen, Jonathan Goh, See-kiong Ng |
| Abstract | Today’s Cyber-Physical Systems (CPSs) are large, complex, and affixed with networked sensors and actuators that are targets for cyber-attacks. Conventional detection techniques are unable to deal with the increasingly dynamic and complex nature of the CPSs. On the other hand, the networked sensors and actuators generate large amounts of data streams that can be continuously monitored for intrusion events. Unsupervised machine learning techniques can be used to model the system behaviour and classify deviant behaviours as possible attacks. In this work, we proposed a novel Generative Adversarial Networks-based Anomaly Detection (GAN-AD) method for such complex networked CPSs. We used LSTM-RNN in our GAN to capture the distribution of the multivariate time series of the sensors and actuators under normal working conditions of a CPS. Instead of treating each sensor’s and actuator’s time series independently, we model the time series of multiple sensors and actuators in the CPS concurrently to take into account of potential latent interactions between them. To exploit both the generator and the discriminator of our GAN, we deployed the GAN-trained discriminator together with the residuals between generator-reconstructed data and the actual samples to detect possible anomalies in the complex CPS. We used our GAN-AD to distinguish abnormal attacked situations from normal working conditions for a complex six-stage Secure Water Treatment (SWaT) system. Experimental results showed that the proposed strategy is effective in identifying anomalies caused by various attacks with high detection rate and low false positive rate as compared to existing methods. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04758v3 |
| http://arxiv.org/pdf/1809.04758v3.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-with-generative-adversarial |
| Repo | https://github.com/LiDan456/GAN-AD |
| Framework | tf |
One-shot Learning for Question-Answering in Gaokao History Challenge
| Title | One-shot Learning for Question-Answering in Gaokao History Challenge |
| Authors | Zhuosheng Zhang, Hai Zhao |
| Abstract | Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics. |
| Tasks | One-Shot Learning, Question Answering |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09105v1 |
| http://arxiv.org/pdf/1806.09105v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-learning-for-question-answering-in |
| Repo | https://github.com/cooelf/OneshotQA |
| Framework | none |
Adversarial Clustering: A Grid Based Clustering Algorithm Against Active Adversaries
| Title | Adversarial Clustering: A Grid Based Clustering Algorithm Against Active Adversaries |
| Authors | Wutao Wei, Bowei Xi, Murat Kantarcioglu |
| Abstract | Nowadays more and more data are gathered for detecting and preventing cyber attacks. In cyber security applications, data analytics techniques have to deal with active adversaries that try to deceive the data analytics models and avoid being detected. The existence of such adversarial behavior motivates the development of robust and resilient adversarial learning techniques for various tasks. Most of the previous work focused on adversarial classification techniques, which assumed the existence of a reasonably large amount of carefully labeled data instances. However, in practice, labeling the data instances often requires costly and time-consuming human expertise and becomes a significant bottleneck. Meanwhile, a large number of unlabeled instances can also be used to understand the adversaries’ behavior. To address the above mentioned challenges, in this paper, we develop a novel grid based adversarial clustering algorithm. Our adversarial clustering algorithm is able to identify the core normal regions, and to draw defensive walls around the centers of the normal objects utilizing game theoretic ideas. Our algorithm also identifies sub-clusters of attack objects, the overlapping areas within clusters, and outliers which may be potential anomalies. |
| Tasks | |
| Published | 2018-04-13 |
| URL | http://arxiv.org/abs/1804.04780v1 |
| http://arxiv.org/pdf/1804.04780v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-clustering-a-grid-based |
| Repo | https://github.com/wutao/ADClust |
| Framework | none |
Real Time Bangladeshi Sign Language Detection using Faster R-CNN
| Title | Real Time Bangladeshi Sign Language Detection using Faster R-CNN |
| Authors | Oishee Bintey Hoque, Mohammad Imrul Jubair, Md. Saiful Islam, Al-Farabi Akash, Alvin Sachie Paulson |
| Abstract | Bangladeshi Sign Language (BdSL) is a commonly used medium of communication for the hearing-impaired people in Bangladesh. Developing a real time system to detect these signs from images is a great challenge. In this paper, we present a technique to detect BdSL from images that performs in real time. Our method uses Convolutional Neural Network based object detection technique to detect the presence of signs in the image region and to recognize its class. For this purpose, we adopted Faster Region-based Convolutional Network approach and developed a dataset $-$ BdSLImset $-$ to train our system. Previous research works in detecting BdSL generally depend on external devices while most of the other vision-based techniques do not perform efficiently in real time. Our approach, however, is free from such limitations and the experimental results demonstrate that the proposed method successfully identifies and recognizes Bangladeshi signs in real time. |
| Tasks | Object Detection |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12813v1 |
| http://arxiv.org/pdf/1811.12813v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-bangladeshi-sign-language-detection |
| Repo | https://github.com/imruljubair/BdSLImset |
| Framework | none |
One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video
| Title | One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video |
| Authors | Wonjoon Goo, Scott Niekum |
| Abstract | Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varying conditions. By contrast, humans are often able to learn complex tasks from a single demonstration (typically observations without action labels) by leveraging context learned over a lifetime. Inspired by this capability, our goal is to enable robots to perform one-shot learning of multi-step tasks from observation by leveraging auxiliary video data as context. Our primary contribution is a novel system that achieves this goal by: (1) using a single user-segmented demonstration to define the primitive actions that comprise a task, (2) localizing additional examples of these actions in unsegmented auxiliary videos via a metalearning-based approach, (3) using these additional examples to learn a reward function for each action, and (4) performing reinforcement learning on top of the inferred reward functions to learn action policies that can be combined to accomplish the task. We empirically demonstrate that a robot can learn multi-step tasks more effectively when provided auxiliary video, and that performance greatly improves when localizing individual actions, compared to learning from unsegmented videos. |
| Tasks | One-Shot Learning |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11244v3 |
| http://arxiv.org/pdf/1806.11244v3.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-learning-of-multi-step-tasks-from |
| Repo | https://github.com/hiwonjoon/ICRA2019-Activity-Localize |
| Framework | tf |
Classifying a specific image region using convolutional nets with an ROI mask as input
| Title | Classifying a specific image region using convolutional nets with an ROI mask as input |
| Authors | Sagi Eppel |
| Abstract | Convolutional neural nets (CNN) are the leading computer vision method for classifying images. In some cases, it is desirable to classify only a specific region of the image that corresponds to a certain object. Hence, assuming that the region of the object in the image is known in advance and is given as a binary region of interest (ROI) mask, the goal is to classify the object in this region using a convolutional neural net. This goal is achieved using a standard image classification net with the addition of a side branch, which converts the ROI mask into an attention map. This map is then combined with the image classification net. This allows the net to focus the attention on the object region while still extracting contextual cues from the background. This approach was evaluated using the COCO object dataset and the OpenSurfaces materials dataset. In both cases, it gave superior results to methods that completely ignore the background region. In addition, it was found that combining the attention map at the first layer of the net gave better results than combining it at higher layers of the net. The advantages of this method are most apparent in the classification of small regions which demands a great deal of contextual information from the background. |
| Tasks | Image Classification |
| Published | 2018-12-01 |
| URL | http://arxiv.org/abs/1812.00291v2 |
| http://arxiv.org/pdf/1812.00291v2.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-a-specific-image-region-using |
| Repo | https://github.com/sagieppel/Classification-of-the-material-given-region-of-an-image-using-a-convolutional-neural-net-with-attent |
| Framework | pytorch |
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
| Title | Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning |
| Authors | Natasha Jaques, Angeliki Lazaridou, Edward Hughes, Caglar Gulcehre, Pedro A. Ortega, DJ Strouse, Joel Z. Leibo, Nando de Freitas |
| Abstract | We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents’ actions. Causal influence is assessed using counterfactual reasoning. At each timestep, an agent simulates alternate actions that it could have taken, and computes their effect on the behavior of other agents. Actions that lead to bigger changes in other agents’ behavior are considered influential and are rewarded. We show that this is equivalent to rewarding agents for having high mutual information between their actions. Empirical results demonstrate that influence leads to enhanced coordination and communication in challenging social dilemma environments, dramatically increasing the learning curves of the deep RL agents, and leading to more meaningful learned communication protocols. The influence rewards for all agents can be computed in a decentralized way by enabling agents to learn a model of other agents using deep neural networks. In contrast, key previous works on emergent communication in the MARL setting were unable to learn diverse policies in a decentralized manner and had to resort to centralized training. Consequently, the influence reward opens up a window of new opportunities for research in this area. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-10-19 |
| URL | https://arxiv.org/abs/1810.08647v4 |
| https://arxiv.org/pdf/1810.08647v4.pdf | |
| PWC | https://paperswithcode.com/paper/social-influence-as-intrinsic-motivation-for |
| Repo | https://github.com/eugenevinitsky/sequential_social_dilemma_games |
| Framework | none |
Assessing Generalization in Deep Reinforcement Learning
| Title | Assessing Generalization in Deep Reinforcement Learning |
| Authors | Charles Packer, Katelyn Gao, Jernej Kos, Philipp Krähenbühl, Vladlen Koltun, Dawn Song |
| Abstract | Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation. The literature lacks a controlled assessment of the merits of different generalization schemes. Our aim is to catalyze community-wide progress on generalization in deep RL. To this end, we present a benchmark and experimental protocol, and conduct a systematic empirical study. Our framework contains a diverse set of environments, our methodology covers both in-distribution and out-of-distribution generalization, and our evaluation includes deep RL algorithms that specifically tackle generalization. Our key finding is that `vanilla’ deep RL algorithms generalize better than specialized schemes that were proposed specifically to tackle generalization. | |
| Tasks | |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12282v2 |
| http://arxiv.org/pdf/1810.12282v2.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-generalization-in-deep |
| Repo | https://github.com/sunblaze-ucb/rl-generalization |
| Framework | tf |
The Power Mean Laplacian for Multilayer Graph Clustering
| Title | The Power Mean Laplacian for Multilayer Graph Clustering |
| Authors | Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein |
| Abstract | Multilayer graphs encode different kind of interactions between the same set of entities. When one wants to cluster such a multilayer graph, the natural question arises how one should merge the information different layers. We introduce in this paper a one-parameter family of matrix power means for merging the Laplacians from different layers and analyze it in expectation in the stochastic block model. We show that this family allows to recover ground truth clusters under different settings and verify this in real world data. While computing the matrix power mean can be very expensive for large graphs, we introduce a numerical scheme to efficiently compute its eigenvectors for the case of large sparse graphs. |
| Tasks | Graph Clustering |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00491v1 |
| http://arxiv.org/pdf/1803.00491v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-power-mean-laplacian-for-multilayer-graph |
| Repo | https://github.com/melopeo/PM |
| Framework | none |
Learning Networks from Random Walk-Based Node Similarities
| Title | Learning Networks from Random Walk-Based Node Similarities |
| Authors | Jeremy G. Hoskins, Cameron Musco, Christopher Musco, Charalampos E. Tsourakakis |
| Abstract | Digital presence in the world of online social media entails significant privacy risks. In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances (i.e., commute times) or personalized PageRank scores. Using these similarities, the attacker’s goal is to infer as much information as possible about the underlying network, including any remaining unknown pairwise node similarities and edges. For the effective resistance metric, we show that with just a small subset of measurements, the attacker can learn a large fraction of edges in a social network, even when the measurements are noisy. We also show that it is possible to learn a graph which accurately matches the underlying network on all other effective resistances. This second observation is interesting from a data mining perspective, since it can be expensive to accurately compute all effective resistances. As an alternative, our graphs learned from just a subset of approximate effective resistances can be used as surrogates in a wide range of applications that use effective resistances to probe graph structure, including for graph clustering, node centrality evaluation, and anomaly detection. We obtain our results by formalizing the graph learning objective mathematically, using two optimization problems. One formulation is convex and can be solved provably in polynomial time. The other is not, but we solve it efficiently with projected gradient and coordinate descent. We demonstrate the effectiveness of these methods on a number of social networks obtained from Facebook. We also discuss how our methods can be generalized to other random walk-based similarities, such as personalized PageRank. Our code is available at https://github.com/cnmusco/graph-similarity-learning. |
| Tasks | Anomaly Detection, Graph Clustering, Graph Similarity |
| Published | 2018-01-23 |
| URL | http://arxiv.org/abs/1801.07386v1 |
| http://arxiv.org/pdf/1801.07386v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-networks-from-random-walk-based-node |
| Repo | https://github.com/cnmusco/graph-similarity-learning |
| Framework | none |
iNNvestigate neural networks!
| Title | iNNvestigate neural networks! |
| Authors | Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele, Kristof T. Schütt, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller, Sven Dähne, Pieter-Jan Kindermans |
| Abstract | In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand and analyze actions and pre- dictions, even of the most complex neural network architectures. Despite these arguments neural networks are often treated as black boxes. In the attempt to alleviate this short- coming many analysis methods were proposed, yet the lack of reference implementations often makes a systematic comparison between the methods a major effort. The presented library iNNvestigate addresses this by providing a common interface and out-of-the- box implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods. To demonstrate the versatility of iNNvestigate, we provide an analysis of image classifications for variety of state-of-the-art neural network architectures. |
| Tasks | Interpretable Machine Learning |
| Published | 2018-08-13 |
| URL | http://arxiv.org/abs/1808.04260v1 |
| http://arxiv.org/pdf/1808.04260v1.pdf | |
| PWC | https://paperswithcode.com/paper/innvestigate-neural-networks |
| Repo | https://github.com/albermax/innvestigate |
| Framework | tf |
Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
| Title | Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models |
| Authors | Lukas Mosser, Olivier Dubrule, Martin J. Blunt |
| Abstract | Geostatistical modeling of petrophysical properties is a key step in modern integrated oil and gas reservoir studies. Recently, generative adversarial networks (GAN) have been shown to be a successful method for generating unconditional simulations of pore- and reservoir-scale models. This contribution leverages the differentiable nature of neural networks to extend GANs to the conditional simulation of three-dimensional pore- and reservoir-scale models. Based on the previous work of Yeh et al. (2016), we use a content loss to constrain to the conditioning data and a perceptual loss obtained from the evaluation of the GAN discriminator network. The technique is tested on the generation of three-dimensional micro-CT images of a Ketton limestone constrained by two-dimensional cross-sections, and on the simulation of the Maules Creek alluvial aquifer constrained by one-dimensional sections. Our results show that GANs represent a powerful method for sampling conditioned pore and reservoir samples for stochastic reservoir evaluation workflows. |
| Tasks | |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05622v1 |
| http://arxiv.org/pdf/1802.05622v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditioning-of-three-dimensional-generative |
| Repo | https://github.com/LukasMosser/geogan |
| Framework | pytorch |
Fast Human Pose Estimation
| Title | Fast Human Pose Estimation |
| Authors | Feng Zhang, Xiatian Zhu, Mao Ye |
| Abstract | Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose. |
| Tasks | Pose Estimation |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05419v2 |
| http://arxiv.org/pdf/1811.05419v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-human-pose-estimation |
| Repo | https://github.com/yuanyuanli85/Fast_Human_Pose_Estimation_Pytorch |
| Framework | pytorch |
Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
| Title | Boredom-driven curious learning by Homeo-Heterostatic Value Gradients |
| Authors | Yen Yu, Acer Y. C. Chang, Ryota Kanai |
| Abstract | This paper presents the Homeo-Heterostatic Value Gradients (HHVG) algorithm as a formal account on the constructive interplay between boredom and curiosity which gives rise to effective exploration and superior forward model learning. We envisaged actions as instrumental in agent’s own epistemic disclosure. This motivated two central algorithmic ingredients: devaluation and devaluation progress, both underpin agent’s cognition concerning intrinsically generated rewards. The two serve as an instantiation of homeostatic and heterostatic intrinsic motivation. A key insight from our algorithm is that the two seemingly opposite motivations can be reconciled—without which exploration and information-gathering cannot be effectively carried out. We supported this claim with empirical evidence, showing that boredom-enabled agents consistently outperformed other curious or explorative agent variants in model building benchmarks based on self-assisted experience accumulation. |
| Tasks | |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01502v1 |
| http://arxiv.org/pdf/1806.01502v1.pdf | |
| PWC | https://paperswithcode.com/paper/boredom-driven-curious-learning-by-homeo |
| Repo | https://github.com/uclyyu/BoredomCuriosity |
| Framework | pytorch |
Composing Text and Image for Image Retrieval - An Empirical Odyssey
| Title | Composing Text and Image for Image Retrieval - An Empirical Odyssey |
| Authors | Nam Vo, Lu Jiang, Chen Sun, Kevin Murphy, Li-Jia Li, Li Fei-Fei, James Hays |
| Abstract | In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar but are modified in small ways, such as being taken at nighttime instead of during the day. To tackle this task, we learn a similarity metric between a target image and a source image plus source text, an embedding and composing function such that target image feature is close to the source image plus text composition feature. We propose a new way to combine image and text using such function that is designed for the retrieval task. We show this outperforms existing approaches on 3 different datasets, namely Fashion-200k, MIT-States and a new synthetic dataset we create based on CLEVR. We also show that our approach can be used to classify input queries, in addition to image retrieval. |
| Tasks | Image Retrieval |
| Published | 2018-12-18 |
| URL | http://arxiv.org/abs/1812.07119v1 |
| http://arxiv.org/pdf/1812.07119v1.pdf | |
| PWC | https://paperswithcode.com/paper/composing-text-and-image-for-image-retrieval |
| Repo | https://github.com/google/tirg |
| Framework | pytorch |
