Paper Group ANR 1074
Adaptive Generation of Phantom Limbs Using Visible Hierarchical Autoencoders. Graph Learning Network: A Structure Learning Algorithm. Efficient Private Algorithms for Learning Large-Margin Halfspaces. FOBE and HOBE: First- and High-Order Bipartite Embeddings. Large Scale Organization and Inference of an Imagery Dataset for Public Safety. Hierarchic …
Adaptive Generation of Phantom Limbs Using Visible Hierarchical Autoencoders
| Title | Adaptive Generation of Phantom Limbs Using Visible Hierarchical Autoencoders |
| Authors | Dakila Ledesma, Yu Liang, Dalei Wu |
| Abstract | This paper proposed a hierarchical visible autoencoder in the adaptive phantom limbs generation according to the kinetic behavior of functional body-parts, which are measured by heterogeneous kinetic sensors. The proposed visible hierarchical autoencoder consists of interpretable and multi-correlated autoencoder pipelines, which is directly derived from the hierarchical network described in forest data-structure. According to specified kinetic script (e.g., dancing, running, etc.) and users’ physical conditions, hierarchical network is extracted from human musculoskeletal network, which is fabricated by multiple body components (e.g., muscle, bone, and joints, etc.) that are bio-mechanically, functionally, or nervously correlated with each other and exhibit mostly non-divergent kinetic behaviors. Multi-layer perceptron (MLP) regressor models, as well as several variations of autoencoder models, are investigated for the sequential generation of missing or dysfunctional limbs. The resulting kinematic behavior of phantom limbs will be constructed using virtual reality and augmented reality (VR/AR), actuators, and potentially controller for a prosthesis (an artificial device that replaces a missing body part). The addressed work aims to develop practical innovative exercise methods that (1) engage individuals at all ages, including those with a chronic health condition(s) and/or disability, in regular physical activities, (2) accelerate the rehabilitation of patients, and (3) release users’ phantom limb pain. The physiological and psychological impact of the addressed work will critically be assessed in future work. |
| Tasks | |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01191v1 |
| https://arxiv.org/pdf/1910.01191v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-generation-of-phantom-limbs-using |
| Repo | |
| Framework | |
Graph Learning Network: A Structure Learning Algorithm
| Title | Graph Learning Network: A Structure Learning Algorithm |
| Authors | Darwin Saire Pilco, Adín Ramírez Rivera |
| Abstract | Recently, graph neural networks (GNNs) have proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static relationships. We propose the Graph Learning Network (GLN), a simple yet effective process to learn node embeddings and structure prediction functions. Our model uses graph convolutions to propose expected node features, and predict the best structure based on them. We repeat these steps recursively to enhance the prediction and the embeddings. |
| Tasks | Community Detection, Link Prediction, Node Classification |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12665v3 |
| https://arxiv.org/pdf/1905.12665v3.pdf | |
| PWC | https://paperswithcode.com/paper/graph-learning-network-a-structure-learning-1 |
| Repo | |
| Framework | |
Efficient Private Algorithms for Learning Large-Margin Halfspaces
| Title | Efficient Private Algorithms for Learning Large-Margin Halfspaces |
| Authors | Huy L. Nguyen, Jonathan Ullman, Lydia Zakynthinou |
| Abstract | We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex optimization, the sample complexity of our algorithms depends only on the margin of the data, and not on the dimension. We complement our results with a lower bound, showing that the dependence of our upper bounds on the margin is optimal. |
| Tasks | |
| Published | 2019-02-24 |
| URL | https://arxiv.org/abs/1902.09009v2 |
| https://arxiv.org/pdf/1902.09009v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-private-algorithms-for-learning |
| Repo | |
| Framework | |
FOBE and HOBE: First- and High-Order Bipartite Embeddings
| Title | FOBE and HOBE: First- and High-Order Bipartite Embeddings |
| Authors | Justin Sybrandt, Ilya Safro |
| Abstract | Typical graph embeddings may not capture type-specific bipartite graph features that arise in such areas as recommender systems, data visualization, and drug discovery. Machine learning methods utilized in these applications would be better served with specialized embedding techniques. We propose two embeddings for bipartite graphs that decompose edges into sets of indirect relationships between node neighborhoods. When sampling higher-order relationships, we reinforce similarities through algebraic distance on graphs. We also introduce ensemble embeddings to combine both into a “best of both worlds” embedding. The proposed methods are evaluated on link prediction and recommendation tasks and compared with other state-of-the-art embeddings. While being all highly beneficial in applications, we demonstrate that none of the considered embeddings is clearly superior (in contrast to what is claimed in many papers), and discuss the trade offs present among them. Reproducibility: Our code, data sets, and results are all publicly available online at: http://bit.ly/fobe_hobe_code. |
| Tasks | Drug Discovery, Link Prediction, Recommendation Systems |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10953v1 |
| https://arxiv.org/pdf/1905.10953v1.pdf | |
| PWC | https://paperswithcode.com/paper/fobe-and-hobe-first-and-high-order-bipartite |
| Repo | |
| Framework | |
Large Scale Organization and Inference of an Imagery Dataset for Public Safety
| Title | Large Scale Organization and Inference of an Imagery Dataset for Public Safety |
| Authors | Jeffrey Liu, David Strohschein, Siddharth Samsi, Andrew Weinert |
| Abstract | Video applications and analytics are routinely projected as a stressing and significant service of the Nationwide Public Safety Broadband Network. As part of a NIST PSCR funded effort, the New Jersey Office of Homeland Security and Preparedness and MIT Lincoln Laboratory have been developing a computer vision dataset of operational and representative public safety scenarios. The scale and scope of this dataset necessitates a hierarchical organization approach for efficient compute and storage. We overview architectural considerations using the Lincoln Laboratory Supercomputing Cluster as a test architecture. We then describe how we intelligently organized the dataset across LLSC and evaluated it with large scale imagery inference across terabytes of data. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.09006v1 |
| https://arxiv.org/pdf/1908.09006v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-organization-and-inference-of-an |
| Repo | |
| Framework | |
Hierarchical Finite State Controllers for Generalized Planning
| Title | Hierarchical Finite State Controllers for Generalized Planning |
| Authors | Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson |
| Abstract | Finite State Controllers (FSCs) are an effective way to represent sequential plans compactly. By imposing appropriate conditions on transitions, FSCs can also represent generalized plans that solve a range of planning problems from a given domain. In this paper we introduce the concept of {\it hierarchical FSCs} for planning by allowing controllers to call other controllers. We show that hierarchical FSCs can represent generalized plans more compactly than individual FSCs. Moreover, our call mechanism makes it possible to generate hierarchical FSCs in a modular fashion, or even to apply recursion. We also introduce a compilation that enables a classical planner to generate hierarchical FSCs that solve challenging generalized planning problems. The compilation takes as input a set of planning problems from a given domain and outputs a single classical planning problem, whose solution corresponds to a hierarchical FSC. |
| Tasks | |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02887v1 |
| https://arxiv.org/pdf/1911.02887v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-finite-state-controllers-for |
| Repo | |
| Framework | |
From exploration to control: learning object manipulation skills through novelty search and local adaptation
| Title | From exploration to control: learning object manipulation skills through novelty search and local adaptation |
| Authors | Seungsu Kim, Alexandre Coninx, Stephane Doncieux |
| Abstract | Programming a robot to deal with open-ended tasks remains a challenge, in particular if the robot has to manipulate objects. Launching, grasping, pushing or any other object interaction can be simulated but the corresponding models are not reversible and the robot behavior thus cannot be directly deduced. These behaviors are hard to learn without a demonstration as the search space is large and the reward sparse. We propose a method to autonomously generate a diverse repertoire of simple object interaction behaviors in simulation. Our goal is to bootstrap a robot learning and development process with limited informations about what the robot has to achieve and how. This repertoire can be exploited to solve different tasks in reality thanks to a proposed adaptation method or could be used as a training set for data-hungry algorithms. The proposed approach relies on the definition of a goal space and generates a repertoire of trajectories to reach attainable goals, thus allowing the robot to control this goal space. The repertoire is built with an off-the-shelf simulation thanks to a quality diversity algorithm. The result is a set of solutions tested in simulation only. It may result in two different problems: (1) as the repertoire is discrete and finite, it may not contain the trajectory to deal with a given situation or (2) some trajectories may lead to a behavior in reality that differs from simulation because of a reality gap. We propose an approach to deal with both issues by using a local linearization between the motion parameters and the observed effects. Furthermore, we present an approach to update the existing solution repertoire with the tests done on the real robot. The approach has been validated on two different experiments on the Baxter robot: a ball launching and a joystick manipulation tasks. |
| Tasks | |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00811v1 |
| http://arxiv.org/pdf/1901.00811v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-exploration-to-control-learning-object |
| Repo | |
| Framework | |
Dropping Pixels for Adversarial Robustness
| Title | Dropping Pixels for Adversarial Robustness |
| Authors | Hossein Hosseini, Sreeram Kannan, Radha Poovendran |
| Abstract | Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness against adversarial examples in all cases of bounded L0, L2 and L_inf perturbations, while reducing the standard accuracy by a small value. We argue that subsampling pixels can be thought to provide a set of robust features for the input image and, thus, improves robustness without performing adversarial training. |
| Tasks | |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.00180v1 |
| http://arxiv.org/pdf/1905.00180v1.pdf | |
| PWC | https://paperswithcode.com/paper/dropping-pixels-for-adversarial-robustness |
| Repo | |
| Framework | |
Double-oracle sampling method for Stackelberg Equilibrium approximation in general-sum extensive-form games
| Title | Double-oracle sampling method for Stackelberg Equilibrium approximation in general-sum extensive-form games |
| Authors | Jan Karwowski, Jacek Mańdziuk |
| Abstract | The paper presents a new method for approximating Strong Stackelberg Equilibrium in general-sum sequential games with imperfect information and perfect recall. The proposed approach is generic as it does not rely on any specific properties of a particular game model. The method is based on iterative interleaving of the two following phases: (1) guided Monte Carlo Tree Search sampling of the Follower’s strategy space and (2) building the Leader’s behavior strategy tree for which the sampled Follower’s strategy is an optimal response. The above solution scheme is evaluated with respect to expected Leader’s utility and time requirements on three sets of interception games with variable characteristics, played on graphs. A comparison with three state-of-the-art MILP/LP-based methods shows that in vast majority of test cases proposed simulation-based approach leads to optimal Leader’s strategies, while excelling the competitive methods in terms of better time scalability and lower memory requirements. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03934v1 |
| https://arxiv.org/pdf/1909.03934v1.pdf | |
| PWC | https://paperswithcode.com/paper/double-oracle-sampling-method-for-stackelberg |
| Repo | |
| Framework | |
The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
| Title | The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation |
| Authors | Sergi Caelles, Jordi Pont-Tuset, Federico Perazzi, Alberto Montes, Kevis-Kokitsi Maninis, Luc Van Gool |
| Abstract | We present the 2019 DAVIS Challenge on Video Object Segmentation, the third edition of the DAVIS Challenge series, a public competition designed for the task of Video Object Segmentation (VOS). In addition to the original semi-supervised track and the interactive track introduced in the previous edition, a new unsupervised multi-object track will be featured this year. In the newly introduced track, participants are asked to provide non-overlapping object proposals on each image, along with an identifier linking them between frames (i.e. video object proposals), without any test-time human supervision (no scribbles or masks provided on the test video). In order to do so, we have re-annotated the train and val sets of DAVIS 2017 in a concise way that facilitates the unsupervised track, and created new test-dev and test-challenge sets for the competition. Definitions, rules, and evaluation metrics for the unsupervised track are described in detail in this paper. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00737v1 |
| https://arxiv.org/pdf/1905.00737v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-2019-davis-challenge-on-vos-unsupervised |
| Repo | |
| Framework | |
Unsupervised Question Answering for Fact-Checking
| Title | Unsupervised Question Answering for Fact-Checking |
| Authors | Mayank Jobanputra |
| Abstract | Recent Deep Learning (DL) models have succeeded in achieving human-level accuracy on various natural language tasks such as question-answering, natural language inference (NLI), and textual entailment. These tasks not only require the contextual knowledge but also the reasoning abilities to be solved efficiently. In this paper, we propose an unsupervised question-answering based approach for a similar task, fact-checking. We transform the FEVER dataset into a Cloze-task by masking named entities provided in the claims. To predict the answer token, we utilize pre-trained Bidirectional Encoder Representations from Transformers (BERT). The classifier computes label based on the correctly answered questions and a threshold. Currently, the classifier is able to classify the claims as “SUPPORTS” and “MANUAL_REVIEW”. This approach achieves a label accuracy of 80.2% on the development set and 80.25% on the test set of the transformed dataset. |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07154v1 |
| https://arxiv.org/pdf/1910.07154v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-question-answering-for-fact |
| Repo | |
| Framework | |
Model Comparison of Dark Energy models Using Deep Network
| Title | Model Comparison of Dark Energy models Using Deep Network |
| Authors | Shi-Yu Li, Yun-Long Li, Tong-Jie Zhang |
| Abstract | This work uses a combination of a variational auto-encoder and generative adversarial network to compare different dark energy models in light of observations, e.g., the distance modulus from type Ia supernovae. The network finds an analytical variational approximation to the true posterior of the latent parameters in the models, yielding consistent model comparison results with those derived by the standard Bayesian method, which suffers from a computationally expensive integral over the parameters in the product of the likelihood and the prior. The parallel computational nature of the network together with the stochastic gradient descent optimization technique leads to an efficient way to compare the physical models given a set of observations. The converged network also provides interpolation for a dataset, which is useful for data reconstruction. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00568v3 |
| https://arxiv.org/pdf/1907.00568v3.pdf | |
| PWC | https://paperswithcode.com/paper/model-comparison-of-dark-energy-models-using |
| Repo | |
| Framework | |
MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs
| Title | MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs |
| Authors | Afshin Sadeghi, Damien Graux, Hamed Shariat Yazdi, Jens Lehmann |
| Abstract | Over the past decade, knowledge graphs became popular for capturing structured domain knowledge. Relational learning models enable the prediction of missing links inside knowledge graphs. More specifically, latent distance approaches model the relationships among entities via a distance between latent representations. Translating embedding models (e.g., TransE) are among the most popular latent distance approaches which use one distance function to learn multiple relation patterns. However, they are mostly inefficient in capturing symmetric relations since the representation vector norm for all the symmetric relations becomes equal to zero. They also lose information when learning relations with reflexive patterns since they become symmetric and transitive. We propose the Multiple Distance Embedding model (MDE) that addresses these limitations and a framework to collaboratively combine variant latent distance-based terms. Our solution is based on two principles: 1) we use a limit-based loss instead of a margin ranking loss and, 2) by learning independent embedding vectors for each of the terms we can collectively train and predict using contradicting distance terms. We further demonstrate that MDE allows modeling relations with (anti)symmetry, inversion, and composition patterns. We propose MDE as a neural network model that allows us to map non-linear relations between the embedding vectors and the expected output of the score function. Our empirical results show that MDE performs competitively to state-of-the-art embedding models on several benchmark datasets. |
| Tasks | Knowledge Graphs, Link Prediction, Relational Reasoning |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10702v8 |
| https://arxiv.org/pdf/1905.10702v8.pdf | |
| PWC | https://paperswithcode.com/paper/mde-multi-distance-embeddings-for-link |
| Repo | |
| Framework | |
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games
| Title | LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games |
| Authors | Leonard Adolphs, Thomas Hofmann |
| Abstract | While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously hard to optimize. With the emerging field of Text-Based Games (TBGs), researchers try to bridge this gap. Inspired by the success of RL algorithms on Atari games, the idea is to develop new methods in a restricted game world and then gradually move to more complex environments. Previous work in the area of TBGs has mainly focused on solving individual games. We, however, consider the task of designing an agent that not just succeeds in a single game, but performs well across a whole family of games, sharing the same theme. In this work, we present our deep RL agent–LeDeepChef–that shows generalization capabilities to never-before-seen games of the same family with different environments and task descriptions. The agent participated in Microsoft Research’s “First TextWorld Problems: A Language and Reinforcement Learning Challenge” and outperformed all but one competitor on the final test set. The games from the challenge all share the same theme, namely cooking in a modern house environment, but differ significantly in the arrangement of the rooms, the presented objects, and the specific goal (recipe to cook). To build an agent that achieves high scores across a whole family of games, we use an actor-critic framework and prune the action-space by using ideas from hierarchical reinforcement learning and a specialized module trained on a recipe database. |
| Tasks | Atari Games, Hierarchical Reinforcement Learning |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01646v1 |
| https://arxiv.org/pdf/1909.01646v1.pdf | |
| PWC | https://paperswithcode.com/paper/ledeepchef-deep-reinforcement-learning-agent |
| Repo | |
| Framework | |
Accelerating small-angle scattering experiments with simulation-based machine learning
| Title | Accelerating small-angle scattering experiments with simulation-based machine learning |
| Authors | Takuya Kanazawa, Akinori Asahara, Hidekazu Morita |
| Abstract | Making material experiments more efficient is a high priority for materials scientists who seek to discover new materials with desirable properties. In this paper, we investigate how to optimize the laborious sequential measurements of materials properties with data-driven methods, taking the small-angle neutron scattering (SANS) experiment as a test case. We propose two methods for optimizing sequential data sampling. These methods iteratively suggest the best target for the next measurement by performing a statistical analysis of the already acquired data, so that maximal information is gained at each step of an experiment. We conducted numerical simulations of SANS experiments for virtual materials and confirmed that the proposed methods significantly outperform baselines. |
| Tasks | |
| Published | 2019-08-24 |
| URL | https://arxiv.org/abs/1908.09102v1 |
| https://arxiv.org/pdf/1908.09102v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-small-angle-scattering |
| Repo | |
| Framework | |
