Paper Group ANR 1031
Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data. Design Space Exploration as Quantified Satisfaction. Conditional Vehicle Trajectories Prediction in CARLA Urban Environment. Learning Vision-based Flight in Drone Swarms by Imitation. Word Usage Similarity Estima …
Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
| Title | Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data |
| Authors | Boyi Liu, Lujia Wang, Ming Liu, Cheng-Zhong Xu |
| Abstract | Humans are capable of learning a new behavior by observing others perform the skill. Robots can also implement this by imitation learning. Furthermore, if with external guidance, humans will master the new behavior more efficiently. So how can robots implement this? To address the issue, we present Federated Imitation Learning (FIL) in the paper. Firstly, a knowledge fusion algorithm deployed on the cloud for fusing knowledge from local robots is presented. Then, effective transfer learning methods in FIL are introduced. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning. FIL considers information privacy and data heterogeneity when robots share knowledge. It is suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a simplified self-driving task for robots (cars). The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems. |
| Tasks | Imitation Learning, Transfer Learning |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.00895v2 |
| https://arxiv.org/pdf/1909.00895v2.pdf | |
| PWC | https://paperswithcode.com/paper/federated-imitation-learning-a-privacy |
| Repo | |
| Framework | |
Design Space Exploration as Quantified Satisfaction
| Title | Design Space Exploration as Quantified Satisfaction |
| Authors | Alexander Feldman, Johan de Kleer, Ion Matei |
| Abstract | We propose novel algorithms for design and design space exploration. The designs computed by these algorithms are compositions of function types specified in component libraries. Our algorithms reduce the design problem to quantified satisfiability and use advanced solvers to find solutions that represent useful systems. The algorithms we present in this paper are sound and complete and are guaranteed to discover correct designs of optimal size, if they exist. We apply our method to the design of Boolean systems and discover new and more optimal classical and quantum circuits for common arithmetic functions such as addition and multiplication. The performance of our algorithms is evaluated through extensive experimentation. We have first created a benchmark consisting of specifications of scalable synthetic digital circuits and real-world mirochips. We have then generated multiple circuits functionally equivalent to the ones in the benchmark. The quantified satisfiability method shows more than four orders of magnitude speed-up, compared to a generate and test method that enumerates all non-isomorphic circuit topologies. Our approach generalizes circuit optimization. It uses arbitrary component libraries and has applications to areas such as digital circuit design, diagnostics, abductive reasoning, test vector generation, and combinatorial optimization. |
| Tasks | Combinatorial Optimization |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02303v2 |
| https://arxiv.org/pdf/1905.02303v2.pdf | |
| PWC | https://paperswithcode.com/paper/design-space-exploration-as-quantified |
| Repo | |
| Framework | |
Conditional Vehicle Trajectories Prediction in CARLA Urban Environment
| Title | Conditional Vehicle Trajectories Prediction in CARLA Urban Environment |
| Authors | Thibault Buhet, Emilie Wirbel, Xavier Perrotton |
| Abstract | Imitation learning is becoming more and more successful for autonomous driving. End-to-end (raw signal to command) performs well on relatively simple tasks (lane keeping and navigation). Mid-to-mid (environment abstraction to mid-level trajectory representation) or direct perception (raw signal to performance) approaches strive to handle more complex, real life environment and tasks (e.g. complex intersection). In this work, we show that complex urban situations can be handled with raw signal input and mid-level representation. We build a hybrid end-to-mid approach predicting trajectories for neighbor vehicles and for the ego vehicle with a conditional navigation goal. We propose an original architecture inspired from social pooling LSTM taking low and mid level data as input and producing trajectories as polynomials of time. We introduce a label augmentation mechanism to get the level of generalization that is required to control a vehicle. The performance is evaluated on CARLA 0.8 benchmark, showing significant improvements over previously published state of the art. |
| Tasks | Autonomous Driving, Imitation Learning |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00792v1 |
| https://arxiv.org/pdf/1909.00792v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-vehicle-trajectories-prediction |
| Repo | |
| Framework | |
Learning Vision-based Flight in Drone Swarms by Imitation
| Title | Learning Vision-based Flight in Drone Swarms by Imitation |
| Authors | Fabian Schilling, Julien Lecoeur, Fabrizio Schiano, Dario Floreano |
| Abstract | Decentralized drone swarms deployed today either rely on sharing of positions among agents or detecting swarm members with the help of visual markers. This work proposes an entirely visual approach to coordinate markerless drone swarms based on imitation learning. Each agent is controlled by a small and efficient convolutional neural network that takes raw omnidirectional images as inputs and predicts 3D velocity commands that match those computed by a flocking algorithm. We start training in simulation and propose a simple yet effective unsupervised domain adaptation approach to transfer the learned controller to the real world. We further train the controller with data collected in our motion capture hall. We show that the convolutional neural network trained on the visual inputs of the drone can learn not only robust inter-agent collision avoidance but also cohesion of the swarm in a sample-efficient manner. The neural controller effectively learns to localize other agents in the visual input, which we show by visualizing the regions with the most influence on the motion of an agent. We remove the dependence on sharing positions among swarm members by taking only local visual information into account for control. Our work can therefore be seen as the first step towards a fully decentralized, vision-based swarm without the need for communication or visual markers. |
| Tasks | Domain Adaptation, Imitation Learning, Motion Capture, Unsupervised Domain Adaptation |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.02999v1 |
| https://arxiv.org/pdf/1908.02999v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-vision-based-flight-in-drone-swarms |
| Repo | |
| Framework | |
Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes
| Title | Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes |
| Authors | Aina Garí Soler, Marianna Apidianaki, Alexandre Allauzen |
| Abstract | Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that leverage these representations for prediction. Our models are further assisted by lexical substitute annotations automatically assigned to word instances by context2vec, a neural model that relies on a bidirectional LSTM. We perform an extensive comparison of existing word and sentence representations on benchmark datasets addressing both graded and binary similarity. The best performing models outperform previous methods in both settings. |
| Tasks | Sentence Embeddings |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08377v1 |
| https://arxiv.org/pdf/1905.08377v1.pdf | |
| PWC | https://paperswithcode.com/paper/word-usage-similarity-estimation-with |
| Repo | |
| Framework | |
DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation
| Title | DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation |
| Authors | Pavel Kirsanov, Airat Gaskarov, Filipp Konokhov, Konstantin Sofiiuk, Anna Vorontsova, Igor Slinko, Dmitry Zhukov, Sergey Bykov, Olga Barinova, Anton Konushin |
| Abstract | We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate the sequences using realistic home layouts. For that we sample trajectories that simulate motions of a simple home robot, and then render the frames along the trajectories. Each data frame contains a) RGB images generated using physically-based rendering, b) simulated depth measurements, c) simulated IMU readings and d) ground truth occupancy grid of a house. Our dataset serves a wider range of purposes compared to existing datasets and is the first large-scale benchmark focused on the mapping component of SLAM. The dataset is split into train/validation/test parts sampled from different sets of virtual houses. We present benchmarking results forboth classical geometry-based and recent learning-based SLAM algorithms, a baseline mapping method, semantic segmentation and panoptic segmentation. |
| Tasks | Panoptic Segmentation, Semantic Segmentation |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.12146v1 |
| https://arxiv.org/pdf/1909.12146v1.pdf | |
| PWC | https://paperswithcode.com/paper/discoman-dataset-of-indoor-scenes-for |
| Repo | |
| Framework | |
KnowBias: A Novel AI Method to Detect Polarity in Online Content
| Title | KnowBias: A Novel AI Method to Detect Polarity in Online Content |
| Authors | Aditya Saligrama |
| Abstract | We propose a novel training and inference method for detecting political bias in long text content such as newspaper opinion articles. Obtaining long text data and annotations at sufficient scale for training is difficult, but it is relatively easy to extract political polarity from tweets through their authorship; as such, we train on tweets and perform inference on articles. Universal sentence encoders and other existing methods that aim to address this domain-adaptation scenario deliver inaccurate and inconsistent predictions on articles, which we show is due to a difference in opinion concentration between tweets and articles. We propose a two-step classification scheme that utilizes a neutral detector trained on tweets to remove neutral sentences from articles in order to align opinion concentration and therefore improve accuracy on that domain. We evaluate our two-step approach using a variety of test suites, including a set of tweets and long-form articles where annotations were crowd-sourced to decrease label noise, measuring accuracy and Spearman-rho rank correlation. In practice, KnowBias achieves a high accuracy of 86 (rho = 0.65) on these tweets and 75 (rho = 0.69) on long-form articles. While we validate our method on political bias, our scheme is general and can be readily applied to other settings, where there exist such domain mismatches between source and target domains. Our implementation is available for public use at https://knowbias.ml. |
| Tasks | Domain Adaptation, Sentence Embeddings, Text Classification |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00724v2 |
| https://arxiv.org/pdf/1905.00724v2.pdf | |
| PWC | https://paperswithcode.com/paper/knowbias-a-novel-ai-method-to-detect-polarity |
| Repo | |
| Framework | |
Lightlike Neuromanifolds, Occam’s Razor and Deep Learning
| Title | Lightlike Neuromanifolds, Occam’s Razor and Deep Learning |
| Authors | Ke Sun, Frank Nielsen |
| Abstract | How do deep neural networks benefit from a very high dimensional parameter space? Their high complexity vs stunning generalization performance forms an intriguing paradox. We took an information-theoretic approach. We find that the locally varying dimensionality of the parameter space can be studied by the discipline of singular semi-Riemannian geometry. We adapt Fisher information to this singular neuromanifold. We use a new prior to interpolate between Jeffreys’ prior and the Gaussian prior. We derive a minimum description length of a deep learning model, where the spectrum of the Fisher information matrix plays a key role to reduce the model complexity. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11027v2 |
| https://arxiv.org/pdf/1905.11027v2.pdf | |
| PWC | https://paperswithcode.com/paper/lightlike-neuromanifolds-occams-razor-and |
| Repo | |
| Framework | |
Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees
| Title | Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees |
| Authors | Changxiao Cai, Gen Li, Yuejie Chi, H. Vincent Poor, Yuxin Chen |
| Abstract | This paper is concerned with estimating the column space of an unknown low-rank matrix $\boldsymbol{A}^{\star}\in\mathbb{R}^{d_{1}\times d_{2}}$, given noisy and partial observations of its entries. There is no shortage of scenarios where the observations — while being too noisy to support faithful recovery of the entire matrix — still convey sufficient information to enable reliable estimation of the column space of interest. This is particularly evident and crucial for the highly unbalanced case where the column dimension $d_{2}$ far exceeds the row dimension $d_{1}$, which is the focal point of the current paper. We investigate an efficient spectral method, which operates upon the sample Gram matrix with diagonal deletion. While this algorithmic idea has been studied before, we establish new statistical guarantees for this method in terms of both $\ell_{2}$ and $\ell_{2,\infty}$ estimation accuracy, which improve upon prior results if $d_{2}$ is substantially larger than $d_{1}$. To illustrate the effectiveness of our findings, we derive matching minimax lower bounds with respect to the noise levels, and develop consequences of our general theory for three applications of practical importance: (1) tensor completion from noisy data, (2) covariance estimation / principal component analysis with missing data, and (3) community recovery in bipartite graphs. Our theory leads to improved performance guarantees for all three cases. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04267v2 |
| https://arxiv.org/pdf/1910.04267v2.pdf | |
| PWC | https://paperswithcode.com/paper/subspace-estimation-from-unbalanced-and |
| Repo | |
| Framework | |
Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
| Title | Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data |
| Authors | Xujiang Zhao, Feng Chen, Jin-Hee Cho |
| Abstract | Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions. Due to high simplicity and applicability, SL has been substantially applied in a variety of decision making in the area of cybersecurity, opinion models, trust models, and/or social network analysis. However, SL and its variants have exposed limitations in predicting uncertain opinions in real-world dynamic network data mainly in three-fold: (1) a lack of scalability to deal with a large-scale network; (2) limited capability to handle heterogeneous topological and temporal dependencies among node-level opinions; and (3) a high sensitivity with conflicting evidence that may generate counterintuitive opinions derived from the evidence. In this work, we proposed a novel deep learning (DL)-based dynamic opinion inference model while node-level opinions are still formalized based on SL meaning that an opinion has a dimension of uncertainty in addition to belief and disbelief in a binomial opinion (i.e., agree or disagree). The proposed DL-based dynamic opinion inference model overcomes the above three limitations by integrating the following techniques: (1) state-of-the-art DL techniques, such as the Graph Convolutional Network (GCN) and the Gated Recurrent Units (GRU) for modeling the topological and temporal heterogeneous dependency information of a given dynamic network; (2) modeling conflicting opinions based on robust statistics; and (3) a highly scalable inference algorithm to predict dynamic, uncertain opinions in a linear computation time. We validated the outperformance of our proposed DL-based algorithm (i.e., GCN-GRU-opinion model) via extensive comparative performance analysis based on four real-world datasets. |
| Tasks | Decision Making |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05640v1 |
| https://arxiv.org/pdf/1910.05640v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-predicting-dynamic |
| Repo | |
| Framework | |
Data Augmentation via Dependency Tree Morphing for Low-Resource Languages
| Title | Data Augmentation via Dependency Tree Morphing for Low-Resource Languages |
| Authors | Gözde Gül Şahin, Mark Steedman |
| Abstract | Neural NLP systems achieve high scores in the presence of sizable training dataset. Lack of such datasets leads to poor system performances in the case low-resource languages. We present two simple text augmentation techniques using dependency trees, inspired from image processing. We crop sentences by removing dependency links, and we rotate sentences by moving the tree fragments around the root. We apply these techniques to augment the training sets of low-resource languages in Universal Dependencies project. We implement a character-level sequence tagging model and evaluate the augmented datasets on part-of-speech tagging task. We show that crop and rotate provides improvements over the models trained with non-augmented data for majority of the languages, especially for languages with rich case marking systems. |
| Tasks | Data Augmentation, Part-Of-Speech Tagging, Text Augmentation |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09460v1 |
| http://arxiv.org/pdf/1903.09460v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-via-dependency-tree-1 |
| Repo | |
| Framework | |
Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
| Title | Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs |
| Authors | Nilesh Chakraborty, Denis Lukovnikov, Gaurav Maheshwari, Priyansh Trivedi, Jens Lehmann, Asja Fischer |
| Abstract | Question answering has emerged as an intuitive way of querying structured data sources, and has attracted significant advancements over the years. In this article, we provide an overview over these recent advancements, focusing on neural network based question answering systems over knowledge graphs. We introduce readers to the challenges in the tasks, current paradigms of approaches, discuss notable advancements, and outline the emerging trends in the field. Through this article, we aim to provide newcomers to the field with a suitable entry point, and ease their process of making informed decisions while creating their own QA system. |
| Tasks | Knowledge Graphs, Question Answering |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09361v1 |
| https://arxiv.org/pdf/1907.09361v1.pdf | |
| PWC | https://paperswithcode.com/paper/introduction-to-neural-network-based |
| Repo | |
| Framework | |
Fashion Outfit Generation for E-commerce
| Title | Fashion Outfit Generation for E-commerce |
| Authors | Elaine M. Bettaney, Stephen R. Hardwick, Odysseas Zisimopoulos, Benjamin Paul Chamberlain |
| Abstract | Combining items of clothing into an outfit is a major task in fashion retail. Recommending sets of items that are compatible with a particular seed item is useful for providing users with guidance and inspiration, but is currently a manual process that requires expert stylists and is therefore not scalable or easy to personalise. We use a multilayer neural network fed by visual and textual features to learn embeddings of items in a latent style space such that compatible items of different types are embedded close to one another. We train our model using the ASOS outfits dataset, which consists of a large number of outfits created by professional stylists and which we release to the research community. Our model shows strong performance in an offline outfit compatibility prediction task. We use our model to generate outfits and for the first time in this field perform an AB test, comparing our generated outfits to those produced by a baseline model which matches appropriate product types but uses no information on style. Users approved of outfits generated by our model 21% and 34% more frequently than those generated by the baseline model for womenswear and menswear respectively. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1904.00741v1 |
| http://arxiv.org/pdf/1904.00741v1.pdf | |
| PWC | https://paperswithcode.com/paper/fashion-outfit-generation-for-e-commerce |
| Repo | |
| Framework | |
TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes
| Title | TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes |
| Authors | Tae Joon Jun, Youngsub Eom, Dohyeun Kim, Cherry Kim, Ji-Hye Park, Hoang Minh Nguyen, Daeyoung Kim |
| Abstract | In this paper, we proposed Transferable Ranking Convolutional Neural Network (TRk-CNN) that can be effectively applied when the classes of images to be classified show a high correlation with each other. The multi-class classification method based on the softmax function, which is generally used, is not effective in this case because the inter-class relationship is ignored. Although there is a Ranking-CNN that takes into account the ordinal classes, it cannot reflect the inter-class relationship to the final prediction. TRk-CNN, on the other hand, combines the weights of the primitive classification model to reflect the inter-class information to the final classification phase. We evaluated TRk-CNN in glaucoma image dataset that was labeled into three classes: normal, glaucoma suspect, and glaucoma eyes. Based on the literature we surveyed, this study is the first to classify three status of glaucoma fundus image dataset into three different classes. We compared the evaluation results of TRk-CNN with Ranking-CNN (Rk-CNN) and multi-class CNN (MC-CNN) using the DenseNet as the backbone CNN model. As a result, TRk-CNN achieved an average accuracy of 92.96%, specificity of 93.33%, sensitivity for glaucoma suspect of 95.12% and sensitivity for glaucoma of 93.98%. Based on average accuracy, TRk-CNN is 8.04% and 9.54% higher than Rk-CNN and MC-CNN and surprisingly 26.83% higher for sensitivity for suspicious than multi-class CNN. Our TRk-CNN is expected to be effectively applied to the medical image classification problem where the disease state is continuous and increases in the positive class direction. |
| Tasks | Image Classification |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06509v1 |
| https://arxiv.org/pdf/1905.06509v1.pdf | |
| PWC | https://paperswithcode.com/paper/trk-cnn-transferable-ranking-cnn-for-image |
| Repo | |
| Framework | |
Dependable Neural Networks for Safety Critical Tasks
| Title | Dependable Neural Networks for Safety Critical Tasks |
| Authors | Molly O’Brien, William Goble, Greg Hager, Julia Bukowski |
| Abstract | Neural Networks are being integrated into safety critical systems, e.g., perception systems for autonomous vehicles, which require trained networks to perform safely in novel scenarios. It is challenging to verify neural networks because their decisions are not explainable, they cannot be exhaustively tested, and finite test samples cannot capture the variation across all operating conditions. Existing work seeks to train models robust to new scenarios via domain adaptation, style transfer, or few-shot learning. But these techniques fail to predict how a trained model will perform when the operating conditions differ from the testing conditions. We propose a metric, Machine Learning (ML) Dependability, that measures the network’s probability of success in specified operating conditions which need not be the testing conditions. In addition, we propose the metrics Task Undependability and Harmful Undependability to distinguish network failures by their consequences. We evaluate the performance of a Neural Network agent trained using Reinforcement Learning in a simulated robot manipulation task. Our results demonstrate that we can accurately predict the ML Dependability, Task Undependability, and Harmful Undependability for operating conditions that are significantly different from the testing conditions. Finally, we design a Safety Function, using harmful failures identified during testing, that reduces harmful failures, in one example, by a factor of 700 while maintaining a high probability of success. |
| Tasks | Autonomous Vehicles, Domain Adaptation, Few-Shot Learning, Style Transfer |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09902v1 |
| https://arxiv.org/pdf/1912.09902v1.pdf | |
| PWC | https://paperswithcode.com/paper/dependable-neural-networks-for-safety |
| Repo | |
| Framework | |
