October 20, 2019

3229 words 16 mins read

Paper Group AWR 313

Online Planner Selection with Graph Neural Networks and Adaptive Scheduling. Learning to Learn from Noisy Labeled Data. Robustness of Quantum-Enhanced Adaptive Phase Estimation. Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning. JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets. …

Online Planner Selection with Graph Neural Networks and Adaptive Scheduling


Title	Online Planner Selection with Graph Neural Networks and Adaptive Scheduling
Authors	Tengfei Ma, Patrick Ferber, Siyu Huo, Jie Chen, Michael Katz
Abstract	Automated planning is one of the foundational areas of AI. Since no single planner can work well for all tasks and domains, portfolio-based techniques have become increasingly popular in recent years. In particular, deep learning emerges as a promising methodology for online planner selection. Owing to the recent development of structural graph representations of planning tasks, we propose a graph neural network (GNN) approach to selecting candidate planners. GNNs are advantageous over a straightforward alternative, the convolutional neural networks, in that they are invariant to node permutations and that they incorporate node labels for better inference. Additionally, for cost-optimal planning, we propose a two-stage adaptive scheduling method to further improve the likelihood that a given task is solved in time. The scheduler may switch at halftime to a different planner, conditioned on the observed performance of the first one. Experimental results validate the effectiveness of the proposed method against strong baselines, both deep learning and non-deep learning based. The code is available at \url{https://github.com/matenure/GNN_planner}.
Tasks
Published	2018-11-01
URL	https://arxiv.org/abs/1811.00210v4
PDF	https://arxiv.org/pdf/1811.00210v4.pdf
PWC	https://paperswithcode.com/paper/online-planner-selection-with-graph-neural
Repo	https://github.com/IBM/IPC-graph-data
Framework	none

Learning to Learn from Noisy Labeled Data


Title	Learning to Learn from Noisy Labeled Data
Authors	Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli
Abstract	Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There exist many inexpensive data sources on the web, but they tend to contain inaccurate labels. Training on noisy labeled datasets causes performance degradation because DNNs can easily overfit to the label noise. To overcome this problem, we propose a noise-tolerant training algorithm, where a meta-learning update is performed prior to conventional gradient update. The proposed meta-learning method simulates actual training by generating synthetic noisy labels, and train the model such that after one gradient update using each set of synthetic noisy labels, the model does not overfit to the specific noise. We conduct extensive experiments on the noisy CIFAR-10 dataset and the Clothing1M dataset. The results demonstrate the advantageous performance of the proposed method compared to several state-of-the-art baselines.
Tasks	Image Classification, Meta-Learning
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05214v2
PDF	http://arxiv.org/pdf/1812.05214v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-learn-from-noisy-labeled-data
Repo	https://github.com/LiJunnan1992/MLNT
Framework	pytorch

Robustness of Quantum-Enhanced Adaptive Phase Estimation


Title	Robustness of Quantum-Enhanced Adaptive Phase Estimation
Authors	Pantita Palittapongarnpim, Barry C. Sanders
Abstract	As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the policies. The robustness test is performed on QEAPE by simulating the scheme under four phase-noise models corresponding to normal-distribution noise, random-telegraph noise, skew-normal-distribution noise, and log-normal-distribution noise. Control policies are devised either by an evolutionary algorithm under the same noisy conditions, albeit ignorant of its properties, or a Bayesian-based feedback method that assumes no noise. Our robustness test and resource comparison method can be used to determining the efficacy and selecting a suitable policy.
Tasks
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05525v2
PDF	http://arxiv.org/pdf/1809.05525v2.pdf
PWC	https://paperswithcode.com/paper/robustness-of-quantum-enhanced-adaptive-phase
Repo	https://github.com/PanPalitta/phase_estimation
Framework	none

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning


Title	Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
Authors	Michael Everett, Yu Fan Chen, Jonathan P. How
Abstract	Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However, they are implemented using key assumptions about other agents’ behavior that deviate from reality as the number of agents in the environment increases. This work extends our previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules. This work also introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. The proposed algorithm outperforms our previous approach in simulation as the number of agents increases, and the algorithm is demonstrated on a fully autonomous robotic vehicle traveling at human walking speed, without the use of a 3D Lidar.
Tasks	Decision Making, Motion Planning
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01956v1
PDF	http://arxiv.org/pdf/1805.01956v1.pdf
PWC	https://paperswithcode.com/paper/motion-planning-among-dynamic-decision-making
Repo	https://github.com/mit-acl/gym-collision-avoidance
Framework	none

JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets


Title	JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Authors	Yunchen Pu, Shuyang Dai, Zhe Gan, Weiyao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin
Abstract	A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional distributions between the domains, while simultaneously learning to sample from the marginals of each individual domain. The proposed framework consists of multiple generators and a single softmax-based critic, all jointly trained via adversarial learning. From a simple noise source, the proposed framework allows synthesis of draws from the marginals, conditional draws given observations from a subset of random variables, or complete draws from the full joint distribution. Most examples considered are for joint analysis of two domains, with examples for three domains also presented.
Tasks
Published	2018-06-08
URL	http://arxiv.org/abs/1806.02978v1
PDF	http://arxiv.org/pdf/1806.02978v1.pdf
PWC	https://paperswithcode.com/paper/jointgan-multi-domain-joint-distribution
Repo	https://github.com/sdai654416/Joint-GAN
Framework	tf

Deeply Informed Neural Sampling for Robot Motion Planning


Title	Deeply Informed Neural Sampling for Robot Motion Planning
Authors	Ahmed H. Qureshi, Michael C. Yip
Abstract	Sampling-based Motion Planners (SMPs) have become increasingly popular as they provide collision-free path solutions regardless of obstacle geometry in a given environment. However, their computational complexity increases significantly with the dimensionality of the motion planning problem. Adaptive sampling is one of the ways to speed up SMPs by sampling a particular region of a configuration space that is more likely to contain an optimal path solution. Although there are a wide variety of algorithms for adaptive sampling, they rely on hand-crafted heuristics; furthermore, their performance decreases significantly in high-dimensional spaces. In this paper, we present a neural network-based adaptive sampler for motion planning called Deep Sampling-based Motion Planner (DeepSMP). DeepSMP generates samples for SMPs and enhances their overall speed significantly while exhibiting efficient scalability to higher-dimensional problems. DeepSMP’s neural architecture comprises of a Contractive AutoEncoder which encodes given workspaces directly from a raw point cloud data, and a Dropout-based stochastic deep feedforward neural network which takes the workspace encoding, start and goal configuration, and iteratively generates feasible samples for SMPs to compute end-to-end collision-free optimal paths. DeepSMP is not only consistently computationally efficient in all tested environments but has also shown remarkable generalization to completely unseen environments. We evaluate DeepSMP on multiple planning problems including planning of a point-mass robot, rigid-body, 6-link robotic manipulator in various 2D and 3D environments. The results show that on average our method is at least 7 times faster in point-mass and rigid-body case and about 28 times faster in 6-link robot case than the existing state-of-the-art.
Tasks	Motion Planning
Published	2018-09-26
URL	http://arxiv.org/abs/1809.10252v1
PDF	http://arxiv.org/pdf/1809.10252v1.pdf
PWC	https://paperswithcode.com/paper/deeply-informed-neural-sampling-for-robot
Repo	https://github.com/ahq1993/MPNet
Framework	pytorch

3D-CODED : 3D Correspondences by Deep Deformation


Title	3D-CODED : 3D Correspondences by Deep Deformation
Authors	Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry
Abstract	We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface. By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template. We show that these correspondences can be improved by an additional step which improves the shape feature by minimizing the Chamfer distance between the input and transformed template. We demonstrate that our simple approach improves on state-of-the-art results on the difficult FAUST-inter challenge, with an average correspondence error of 2.88cm. We show, on the TOSCA dataset, that our method is robust to many types of perturbations, and generalizes to non-human shapes. This robustness allows it to perform well on real unclean, meshes from the the SCAPE dataset.
Tasks	3D Human Pose Estimation, 3D Point Cloud Matching, 3D Surface Generation
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05228v2
PDF	http://arxiv.org/pdf/1806.05228v2.pdf
PWC	https://paperswithcode.com/paper/3d-coded-3d-correspondences-by-deep-1
Repo	https://github.com/ThibaultGROUEIX/3D-CODED
Framework	pytorch

Adversarial Soft-detection-based Aggregation Network for Image Retrieval


Title	Adversarial Soft-detection-based Aggregation Network for Image Retrieval
Authors	Jian Xu, Chunheng Wang, Cunzhao Shi, Baihua Xiao
Abstract	In recent year, the compact representations based on activations of Convolutional Neural Network (CNN) achieve remarkable performance in image retrieval. However, retrieval of some interested object that only takes up a small part of the whole image is still a challenging problem. Therefore, it is significant to extract the discriminative representations that contain regional information of the pivotal small object. In this paper, we propose a novel adversarial soft-detection-based aggregation (ASDA) method free from bounding box annotations for image retrieval, based on adversarial detector and soft region proposal layer. Our trainable adversarial detector generates semantic maps based on adversarial erasing strategy to preserve more discriminative and detailed information. Computed based on semantic maps corresponding to various discriminative patterns and semantic contents, our soft region proposal is arbitrary shape rather than only rectangle and it reflects the significance of objects. The aggregation based on trainable soft region proposal highlights discriminative semantic contents and suppresses the noise of background. We conduct comprehensive experiments on standard image retrieval datasets. Our weakly supervised ASDA method achieves state-of-the-art performance on most datasets. The results demonstrate that the proposed ASDA method is effective for image retrieval.
Tasks	Image Retrieval
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07619v3
PDF	http://arxiv.org/pdf/1811.07619v3.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-soft-detection-based
Repo	https://github.com/hbwang1427/image_retrieval
Framework	none

Explicit Interaction Model towards Text Classification


Title	Explicit Interaction Model towards Text Classification
Authors	Cunxiao Du, Zhaozheng Chin, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie
Abstract	Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance of deep models, they ignore the fine-grained (matching signals between words and classes) classification clues since their classifications mainly rely on the text-level representations. To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task. In particular, we design a novel framework, EXplicit interAction Model (dubbed as EXAM), equipped with the interaction mechanism. We justified the proposed approach on several benchmark datasets including both multi-label and multi-class text classification tasks. Extensive experimental results demonstrate the superiority of the proposed method. As a byproduct, we have released the codes and parameter settings to facilitate other researches.
Tasks	Sentiment Analysis, Text Classification
Published	2018-11-23
URL	http://arxiv.org/abs/1811.09386v1
PDF	http://arxiv.org/pdf/1811.09386v1.pdf
PWC	https://paperswithcode.com/paper/explicit-interaction-model-towards-text
Repo	https://github.com/NonvolatileMemory/AAAI_2019_EXAM
Framework	tf

Learning Dynamics of Linear Denoising Autoencoders


Title	Learning Dynamics of Linear Denoising Autoencoders
Authors	Arnu Pretorius, Steve Kroon, Herman Kamper
Abstract	Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences learning in DAEs. By focusing on linear DAEs, we are able to derive analytic expressions that exactly describe their learning dynamics. We verify our theoretical predictions with simulations as well as experiments on MNIST and CIFAR-10. The theory illustrates how, when tuned correctly, noise allows DAEs to ignore low variance directions in the inputs while learning to reconstruct them. Furthermore, in a comparison of the learning dynamics of DAEs to standard regularised autoencoders, we show that noise has a similar regularisation effect to weight decay, but with faster training dynamics. We also show that our theoretical predictions approximate learning dynamics on real-world data and qualitatively match observed dynamics in nonlinear DAEs.
Tasks	Denoising, Representation Learning, Unsupervised Representation Learning
Published	2018-06-14
URL	http://arxiv.org/abs/1806.05413v2
PDF	http://arxiv.org/pdf/1806.05413v2.pdf
PWC	https://paperswithcode.com/paper/learning-dynamics-of-linear-denoising
Repo	https://github.com/arnupretorius/lindaedynamics_icml2018
Framework	none

Node Embedding with Adaptive Similarities for Scalable Learning over Graphs


Title	Node Embedding with Adaptive Similarities for Scalable Learning over Graphs
Authors	Dimitris Berberidis, Georgios B. Giannakis
Abstract	Node embedding is the task of extracting informative and descriptive features over the nodes of a graph. The importance of node embeddings for graph analytics, as well as learning tasks such as node classification, link prediction and community detection, has led to increased interest on the problem leading to a number of recent advances. Much like PCA in the feature domain, node embedding is an inherently \emph{unsupervised} task; in lack of metadata used for validation, practical methods may require standardization and limiting the use of tunable hyperparameters. Finally, node embedding methods are faced with maintaining scalability in the face of large-scale real-world graphs of ever-increasing sizes. In the present work, we propose an adaptive node embedding framework that adjusts the embedding process to a given underlying graph, in a fully unsupervised manner. To achieve this, we adopt the notion of a tunable node similarity matrix that assigns weights on paths of different length. The design of the multilength similarities ensures that the resulting embeddings also inherit interpretable spectral properties. The proposed model is carefully studied, interpreted, and numerically evaluated using stochastic block models. Moreover, an algorithmic scheme is proposed for training the model parameters effieciently and in an unsupervised manner. We perform extensive node classification, link prediction, and clustering experiments on many real world graphs from various domains, and compare with state-of-the-art scalable and unsupervised node embedding alternatives. The proposed method enjoys superior performance in many cases, while also yielding interpretable information on the underlying structure of the graph.
Tasks	Community Detection, Link Prediction, Node Classification
Published	2018-11-27
URL	https://arxiv.org/abs/1811.10797v3
PDF	https://arxiv.org/pdf/1811.10797v3.pdf
PWC	https://paperswithcode.com/paper/node-embedding-with-adaptive-similarities-for
Repo	https://github.com/DimBer/ASE-project
Framework	none

Structured Pruning for Efficient ConvNets via Incremental Regularization


Title	Structured Pruning for Efficient ConvNets via Incremental Regularization
Authors	Huan Wang, Qiming Zhang, Yuehai Wang, Yu Lu, Haoji Hu
Abstract	Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fragility of the expressiveness of CNNs, and thus calls for a more gentle regularization scheme so that the networks can adapt during pruning. To achieve this, we propose a new and novel regularization-based pruning method, named IncReg, to incrementally assign different regularization factors to different weights based on their relative importance. Empirical analysis on CIFAR-10 dataset verifies the merits of IncReg. Further extensive experiments with popular CNNs on CIFAR-10 and ImageNet datasets show that IncReg achieves comparable to even better results compared with state-of-the-arts. Our source codes and trained models are available here: https://github.com/mingsun-tse/caffe_increg.
Tasks	Network Pruning
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09461v2
PDF	http://arxiv.org/pdf/1804.09461v2.pdf
PWC	https://paperswithcode.com/paper/structured-deep-neural-network-pruning-by
Repo	https://github.com/MingSun-Tse/Caffe_IncReg
Framework	none

Scalable Methods for 8-bit Training of Neural Networks


Title	Scalable Methods for 8-bit Training of Neural Networks
Authors	Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
Abstract	Quantized Neural Networks (QNNs) are often used to improve network efficiency during the inference phase, i.e. after the network has been trained. Extensive research in the field suggests many different quantization schemes. Still, the number of bits required, as well as the best quantization scheme, are yet unknown. Our theoretical analysis suggests that most of the training process is robust to substantial precision reduction, and points to only a few specific operations that require higher precision. Armed with this knowledge, we quantize the model parameters, activations and layer gradients to 8-bit, leaving at a higher precision only the final step in the computation of the weight gradients. Additionally, as QNNs require batch-normalization to be trained at high precision, we introduce Range Batch-Normalization (BN) which has significantly higher tolerance to quantization noise and improved computational complexity. Our simulations show that Range BN is equivalent to the traditional batch norm if a precise scale adjustment, which can be approximated analytically, is applied. To the best of the authors’ knowledge, this work is the first to quantize the weights, activations, as well as a substantial volume of the gradients stream, in all layers (including batch normalization) to 8-bit while showing state-of-the-art results over the ImageNet-1K dataset.
Tasks	Quantization
Published	2018-05-25
URL	http://arxiv.org/abs/1805.11046v3
PDF	http://arxiv.org/pdf/1805.11046v3.pdf
PWC	https://paperswithcode.com/paper/scalable-methods-for-8-bit-training-of-neural
Repo	https://github.com/eladhoffer/quantized.pytorch
Framework	pytorch

Open Category Detection with PAC Guarantees


Title	Open Category Detection with PAC Guarantees
Authors	Si Liu, Risheek Garrepalli, Thomas G. Dietterich, Alan Fern, Dan Hendrycks
Abstract	Open category detection is the problem of detecting “alien” test instances that belong to categories or classes that were not present in the training data. In many applications, reliably detecting such aliens is central to ensuring the safety and accuracy of test set predictions. Unfortunately, there are no algorithms that provide theoretical guarantees on their ability to detect aliens under general assumptions. Further, while there are algorithms for open category detection, there are few empirical results that directly report alien detection rates. Thus, there are significant theoretical and empirical gaps in our understanding of open category detection. In this paper, we take a step toward addressing this gap by studying a simple, but practically-relevant variant of open category detection. In our setting, we are provided with a “clean” training set that contains only the target categories of interest and an unlabeled “contaminated” training set that contains a fraction $\alpha$ of alien examples. Under the assumption that we know an upper bound on $\alpha$, we develop an algorithm with PAC-style guarantees on the alien detection rate, while aiming to minimize false alarms. Empirical results on synthetic and standard benchmark datasets demonstrate the regimes in which the algorithm can be effective and provide a baseline for further advancements.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00529v1
PDF	http://arxiv.org/pdf/1808.00529v1.pdf
PWC	https://paperswithcode.com/paper/open-category-detection-with-pac-guarantees
Repo	https://github.com/liusi2019/ocd
Framework	none

An Overview and a Benchmark of Active Learning for Outlier Detection with One-Class Classifiers


Title	An Overview and a Benchmark of Active Learning for Outlier Detection with One-Class Classifiers
Authors	Holger Trittenbach, Adrian Englhardt, Klemens Böhm
Abstract	Active learning methods increase classification quality by means of user feedback. An important subcategory is active learning for outlier detection with one-class classifiers. While various methods in this category exist, selecting one for a given application scenario is difficult. This is because existing methods rely on different assumptions, have different objectives, and often are tailored to a specific use case. All this calls for a comprehensive comparison, the topic of this article. This article starts with a categorization of the various methods. We then propose ways to evaluate active learning results. Next, we run extensive experiments to compare existing methods, for a broad variety of scenarios. Based on our results, we formulate guidelines on how to select active learning methods for outlier detection with one-class classifiers.
Tasks	Active Learning, Outlier Detection
Published	2018-08-14
URL	https://arxiv.org/abs/1808.04759v2
PDF	https://arxiv.org/pdf/1808.04759v2.pdf
PWC	https://paperswithcode.com/paper/an-overview-and-a-benchmark-of-active
Repo	https://github.com/kit-dbis/ocal-evaluation
Framework	none