February 1, 2020

3162 words 15 mins read

Paper Group AWR 266

Learning to Propagate for Graph Meta-Learning. MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III. Evaluating Coherence in Dialogue Systems using Entailment. Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning. Semi-Supervised Segmentation of Salt Bodi …

Learning to Propagate for Graph Meta-Learning


Title	Learning to Propagate for Graph Meta-Learning
Authors	Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang
Abstract	Meta-learning extracts common knowledge from learning different tasks and uses it for unseen tasks. It can significantly improve tasks that suffer from insufficient training data, e.g., few shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve few shot learning. The graph’s structure is usually free or cheap to obtain but has rarely been explored in previous works. We develop a novel meta-learner of this type for prototype-based classification, in which a prototype is generated for each class, such that the nearest neighbor search among the prototypes produces an accurate classification. The meta-learner, called “Gated Propagation Network (GPN)", learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism aggregates messages from neighboring classes of each class, with a gate choosing between the aggregated message and the message from the class itself. We train GPN on a sequence of tasks from many-shot to few shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, under different training-test discrepancy and test task generation settings, GPN outperforms recent meta-learning methods on two benchmark datasets. The code of GPN and dataset generation is available at https://github.com/liulu112601/Gated-Propagation-Net.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Meta-Learning
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05024v2
PDF	https://arxiv.org/pdf/1909.05024v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-propagate-for-graph-meta-learning
Repo	https://github.com/liulu112601/Gated-Propagation-Net
Framework	pytorch

MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III


Title	MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III
Authors	Shirly Wang, Matthew B. A. McDermott, Geeticka Chauhan, Michael C. Hughes, Tristan Naumann, Marzyeh Ghassemi
Abstract	Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose performance can be reasonably reproduced. In machine learning for healthcare, the community faces reproducibility challenges due to a lack of publicly accessible data and a lack of standardized data processing frameworks. We present MIMIC-Extract, an open-source pipeline for transforming raw electronic health record (EHR) data for critical care patients contained in the publicly-available MIMIC-III database into dataframes that are directly usable in common machine learning pipelines. MIMIC-Extract addresses three primary challenges in making complex health records data accessible to the broader machine learning community. First, it provides standardized data processing functions, including unit conversion, outlier detection, and aggregating semantically equivalent features, thus accounting for duplication and reducing missingness. Second, it preserves the time series nature of clinical data and can be easily integrated into clinically actionable prediction tasks in machine learning for health. Finally, it is highly extensible so that other researchers with related questions can easily use the same pipeline. We demonstrate the utility of this pipeline by showcasing several benchmark tasks and baseline results.
Tasks	Length-of-Stay prediction, Outlier Detection, Time Series
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08322v1
PDF	https://arxiv.org/pdf/1907.08322v1.pdf
PWC	https://paperswithcode.com/paper/mimic-extract-a-data-extraction-preprocessing
Repo	https://github.com/MLforHealth/MIMIC_Extract
Framework	none

Evaluating Coherence in Dialogue Systems using Entailment


Title	Evaluating Coherence in Dialogue Systems using Entailment
Authors	Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson, Osmar Zaiane
Abstract	Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resulting in a significant bias across different models and datasets. Some researchers resort to human judgment experimentation for assessing response quality, which is expensive, time consuming, and not scalable. Moreover, judges tend to evaluate a small number of dialogues, meaning that minor differences in evaluation configuration may lead to dissimilar results. In this paper, we present interpretable metrics for evaluating topic coherence by making use of distributed sentence representations. Furthermore, we introduce calculable approximations of human judgment based on conversational coherence by adopting state-of-the-art entailment techniques. Results show that our metrics can be used as a surrogate for human judgment, making it easy to evaluate dialogue systems on large-scale datasets and allowing an unbiased estimate for the quality of the responses.
Tasks
Published	2019-04-06
URL	https://arxiv.org/abs/1904.03371v2
PDF	https://arxiv.org/pdf/1904.03371v2.pdf
PWC	https://paperswithcode.com/paper/evaluating-coherence-in-dialogue-systems
Repo	https://github.com/nouhadziri/DialogEntailment
Framework	pytorch

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning


Title	Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning
Authors	Zhuoren Jiang, Jian Wang, Lujun Zhao, Changlong Sun, Yao Lu, Xiaozhong Liu
Abstract	Aspect category detection is an essential task for sentiment analysis and opinion mining. However, the cost of categorical data labeling, e.g., label the review aspect information for a large number of product domains, can be inevitable but unaffordable. In this study, we propose a novel problem, cross-domain aspect category transfer and detection, which faces three challenges: various feature spaces, different data distributions, and diverse output spaces. To address these problems, we propose an innovative solution, Traceable Heterogeneous Graph Representation Learning (THGRL). Unlike prior text-based aspect detection works, THGRL explores latent domain aspect category connections via massive user behavior information on a heterogeneous graph. Moreover, an innovative latent variable “Walker Tracer” is introduced to characterize the global semantic/aspect dependencies and capture the informative vertexes on the random walk paths. By using THGRL, we project different domains’ feature spaces into a common one, while allowing data distributions and output spaces stay differently. Experiment results show that the proposed method outperforms a series of state-of-the-art baseline models.
Tasks	Graph Representation Learning, Opinion Mining, Representation Learning, Sentiment Analysis
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11610v1
PDF	https://arxiv.org/pdf/1908.11610v1.pdf
PWC	https://paperswithcode.com/paper/cross-domain-aspect-category-transfer-and
Repo	https://github.com/lzswangjian/THGRL
Framework	none

Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks


Title	Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks
Authors	Yauhen Babakhin, Artsiom Sanakoyeu, Hirotoshi Kitamura
Abstract	Seismic image analysis plays a crucial role in a wide range of industrial applications and has been receiving significant attention. One of the essential challenges of seismic imaging is detecting subsurface salt structure which is indispensable for identification of hydrocarbon reservoirs and drill path planning. Unfortunately, exact identification of large salt deposits is notoriously difficult and professional seismic imaging often requires expert human interpretation of salt bodies. Convolutional neural networks (CNNs) have been successfully applied in many fields, and several attempts have been made in the field of seismic imaging. But the high cost of manual annotations by geophysics experts and scarce publicly available labeled datasets hinder the performance of the existing CNN-based methods. In this work, we propose a semi-supervised method for segmentation (delineation) of salt bodies in seismic images which utilizes unlabeled data for multi-round self-training. To reduce error amplification during self-training we propose a scheme which uses an ensemble of CNNs. We show that our approach outperforms state-of-the-art on the TGS Salt Identification Challenge dataset and is ranked the first among the 3234 competing methods.
Tasks
Published	2019-04-09
URL	https://arxiv.org/abs/1904.04445v3
PDF	https://arxiv.org/pdf/1904.04445v3.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-segmentation-of-salt-bodies
Repo	https://github.com/ybabakhin/kaggle_salt_bes_phalanx
Framework	none

A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements


Title	A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements
Authors	Romain Lopez, Achille Nazaret, Maxime Langevin, Jules Samaran, Jeffrey Regier, Michael I. Jordan, Nir Yosef
Abstract	Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most experimental protocols for spatial transcriptomics suffer from the need to select beforehand a small fraction of genes to be quantified over the entire transcriptome. Standard single-cell RNA sequencing (scRNA-seq) is more prevalent, easier to implement and can in principle capture any gene but cannot recover the spatial location of the cells. In this manuscript, we focus on the problem of imputation of missing genes in spatial transcriptomic data based on (unpaired) standard scRNA-seq data from the same biological tissue. Building upon domain adaptation work, we propose gimVI, a deep generative model for the integration of spatial transcriptomic data and scRNA-seq data that can be used to impute missing genes. After describing our generative model and an inference procedure for it, we compare gimVI to alternative methods from computational biology or domain adaptation on real datasets and outperform Seurat Anchors, Liger and CORAL to impute held-out genes.
Tasks	Domain Adaptation, Imputation
Published	2019-05-06
URL	https://arxiv.org/abs/1905.02269v1
PDF	https://arxiv.org/pdf/1905.02269v1.pdf
PWC	https://paperswithcode.com/paper/a-joint-model-of-unpaired-data-from-scrna-seq
Repo	https://github.com/YosefLab/scVI
Framework	pytorch

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling


Title	Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
Authors	Yuping Luo, Huazhe Xu, Tengyu Ma
Abstract	Imitation learning, followed by reinforcement learning algorithms, is a promising paradigm to solve complex control tasks sample-efficiently. However, learning from demonstrations often suffers from the covariate shift problem, which results in cascading errors of the learned policy. We introduce a notion of conservatively-extrapolated value functions, which provably lead to policies with self-correction. We design an algorithm Value Iteration with Negative Sampling (VINS) that practically learns such value functions with conservative extrapolation. We show that VINS can correct mistakes of the behavioral cloning policy on simulated robotics benchmark tasks. We also propose the algorithm of using VINS to initialize a reinforcement learning algorithm, which is shown to outperform significantly prior works in sample efficiency.
Tasks	Imitation Learning
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05634v3
PDF	https://arxiv.org/pdf/1907.05634v3.pdf
PWC	https://paperswithcode.com/paper/learning-self-correctable-policies-and-value
Repo	https://github.com/BCHoagland/VINS
Framework	pytorch

Unsupervised Data Imputation via Variational Inference of Deep Subspaces


Title	Unsupervised Data Imputation via Variational Inference of Deep Subspaces
Authors	Adrian V. Dalca, John Guttag, Mert R. Sabuncu
Abstract	A wide range of systems exhibit high dimensional incomplete data. Accurate estimation of the missing data is often desired, and is crucial for many downstream analyses. Many state-of-the-art recovery methods involve supervised learning using datasets containing full observations. In contrast, we focus on unsupervised estimation of missing image data, where no full observations are available - a common situation in practice. Unsupervised imputation methods for images often employ a simple linear subspace to capture correlations between data dimensions, omitting more complex relationships. In this work, we introduce a general probabilistic model that describes sparse high dimensional imaging data as being generated by a deep non-linear embedding. We derive a learning algorithm using a variational approximation based on convolutional neural networks and discuss its relationship to linear imputation models, the variational auto encoder, and deep image priors. We introduce sparsity-aware network building blocks that explicitly model observed and missing data. We analyze proposed sparsity-aware network building blocks, evaluate our method on public domain imaging datasets, and conclude by showing that our method enables imputation in an important real-world problem involving medical images. The code is freely available as part of the \verbneuron library at http://github.com/adalca/neuron.
Tasks	Imputation
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03503v1
PDF	http://arxiv.org/pdf/1903.03503v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-data-imputation-via-variational
Repo	https://github.com/adalca/neuron
Framework	tf

A novel centroid update approach for clustering-based superpixel method and superpixel-based edge detection


Title	A novel centroid update approach for clustering-based superpixel method and superpixel-based edge detection
Authors	Houwang Zhang, Chong Wu, Le Zhang, Hanying Zheng
Abstract	Superpixel is widely used in image processing. And among the methods for superpixel generation, clustering-based methods have a high speed and a good performance at the same time. However, most clustering-based superpixel methods are sensitive to noise. To solve these problems, in this paper, we first analyze the features of noise. Then according to the statistical features of noise, we propose a novel centroid updating approach to enhance the robustness of the clustering-based superpixel methods. Besides, we propose a novel superpixel based edge detection method. The experiments on BSD500 dataset show that our approach can significantly enhance the performance of clustering-based superpixel methods in noisy environment. Moreover, we also show that our proposed edge detection method outperforms other classical methods.
Tasks	Edge Detection
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08439v1
PDF	https://arxiv.org/pdf/1910.08439v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-centroid-update-approach-for
Repo	https://github.com/ProfHubert/ICASSP
Framework	none

Specifying Object Attributes and Relations in Interactive Scene Generation


Title	Specifying Object Attributes and Relations in Interactive Scene Generation
Authors	Oron Ashual, Lior Wolf
Abstract	We introduce a method for the generation of images from an input scene graph. The method separates between a layout embedding and an appearance embedding. The dual embedding leads to generated images that better match the scene graph, have higher visual quality, and support more complex scene graphs. In addition, the embedding scheme supports multiple and diverse output images per scene graph, which can be further controlled by the user. We demonstrate two modes of per-object control: (i) importing elements from other images, and (ii) navigation in the object space, by selecting an appearance archetype. Our code is publicly available at https://www.github.com/ashual/scene_generation
Tasks	Layout-to-Image Generation, Scene Generation
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05379v2
PDF	https://arxiv.org/pdf/1909.05379v2.pdf
PWC	https://paperswithcode.com/paper/specifying-object-attributes-and-relations-in
Repo	https://github.com/ashual/scene_generation
Framework	pytorch

Asymmetric Non-local Neural Networks for Semantic Segmentation


Title	Asymmetric Non-local Neural Networks for Semantic Segmentation
Authors	Zhen Zhu, Mengde Xu, Song Bai, Tengteng Huang, Xiang Bai
Abstract	The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, which has two prominent components: Asymmetric Pyramid Non-local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB). APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance. AFNB is adapted from APNB to fuse the features of different levels under a sufficient consideration of long range dependencies and thus considerably improves the performance. Extensive experiments on semantic segmentation benchmarks demonstrate the effectiveness and efficiency of our work. In particular, we report the state-of-the-art performance of 81.3 mIoU on the Cityscapes test set. For a 256x128 input, APNB is around 6 times faster than a non-local block on GPU while 28 times smaller in GPU running memory occupation. Code is available at: https://github.com/MendelXu/ANN.git.
Tasks	Semantic Segmentation
Published	2019-08-21
URL	https://arxiv.org/abs/1908.07678v5
PDF	https://arxiv.org/pdf/1908.07678v5.pdf
PWC	https://paperswithcode.com/paper/asymmetric-non-local-neural-networks-for
Repo	https://github.com/MendelXu/ANN
Framework	pytorch

Self-Critical Reasoning for Robust Visual Question Answering


Title	Self-Critical Reasoning for Robust Visual Question Answering
Authors	Jialin Wu, Raymond J. Mooney
Abstract	Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different question-answer (QA) distribution. To address this issue, we introduce a self-critical training objective that ensures that visual explanations of correct answers match the most influential image regions more than other competitive answer candidates. The influential regions are either determined from human visual/textual explanations or automatically from just significant words in the question and answer. We evaluate our approach on the VQA generalization task using the VQA-CP dataset, achieving a new state-of-the-art i.e., 49.5% using textual explanations and 48.5% using automatically annotated regions.
Tasks	Question Answering, Visual Question Answering
Published	2019-05-24
URL	https://arxiv.org/abs/1905.09998v3
PDF	https://arxiv.org/pdf/1905.09998v3.pdf
PWC	https://paperswithcode.com/paper/self-critical-reasoning-for-robust-visual
Repo	https://github.com/jialinwu17/Self_Critical_VQA
Framework	pytorch

Mask-Guided Attention Network for Occluded Pedestrian Detection


Title	Mask-Guided Attention Network for Occluded Pedestrian Detection
Authors	Yanwei Pang, Jin Xie, Muhammad Haris Khan, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao
Abstract	Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance on heavily occluded pedestrians remains far from satisfactory. The main culprits are intra-class occlusions involving other pedestrians and inter-class occlusions caused by other objects, such as cars and bicycles. These result in a multitude of occlusion patterns. We propose an approach for occluded pedestrian detection with the following contributions. First, we introduce a novel mask-guided attention network that fits naturally into popular pedestrian detection pipelines. Our attention network emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features. Second, we empirically demonstrate that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts. Experiments are performed on CityPersons and Caltech datasets. Our approach sets a new state-of-the-art on both datasets. Our approach obtains an absolute gain of 9.5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set. Further, on the HO pedestrian set of Caltech dataset, our method achieves an absolute gain of 5.0% in log-average miss rate, compared to the best reported results. Code and models are available at: https://github.com/Leotju/MGAN.
Tasks	Pedestrian Detection
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06160v2
PDF	https://arxiv.org/pdf/1910.06160v2.pdf
PWC	https://paperswithcode.com/paper/mask-guided-attention-network-for-occluded
Repo	https://github.com/Leotju/MGAN
Framework	pytorch

Tree Search vs Optimization Approaches for Map Generation


Title	Tree Search vs Optimization Approaches for Map Generation
Authors	Debosmita Bhaumik, Ahmed Khalifa, Michael Cerny Green, Julian Togelius
Abstract	Search-based procedural content generation uses stochastic global optimization algorithms to search spaces of game content. However, it has been found that tree search can be competitive with evolution on certain optimization problems. We investigate the applicability of several tree search methods to map generation and compare them systematically with several optimization algorithms, including evolutionary algorithms. For purposes of comparison, we use a simplified map generation problem where only passable and impassable tiles exist, three different map representations, and a set of objectives that are representative of those commonly found in actual level generation problem. While the results suggest that evolutionary algorithms produce good maps faster, several tree search methods can perform very well given sufficient time, and there are interesting differences in the character of the generated maps depending on the algorithm chosen, even for the same representation and objective.
Tasks
Published	2019-03-27
URL	https://arxiv.org/abs/1903.11678v2
PDF	https://arxiv.org/pdf/1903.11678v2.pdf
PWC	https://paperswithcode.com/paper/tree-search-vs-optimization-approaches-for
Repo	https://github.com/amidos2006/gym-pcgrl
Framework	tf

Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces


Title	Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
Authors	Johannes Kirschner, Mojmír Mutný, Nicole Hiller, Rasmus Ischebeck, Andreas Krause
Abstract	Bayesian optimization is known to be difficult to scale to high dimensions, because the acquisition step requires solving a non-convex optimization problem in the same search space. In order to scale the method and keep its benefits, we propose an algorithm (LineBO) that restricts the problem to a sequence of iteratively chosen one-dimensional sub-problems that can be solved efficiently. We show that our algorithm converges globally and obtains a fast local rate when the function is strongly convex. Further, if the objective has an invariant subspace, our method automatically adapts to the effective dimension without changing the algorithm. When combined with the SafeOpt algorithm to solve the sub-problems, we obtain the first safe Bayesian optimization algorithm with theoretical guarantees applicable in high-dimensional settings. We evaluate our method on multiple synthetic benchmarks, where we obtain competitive performance. Further, we deploy our algorithm to optimize the beam intensity of the Swiss Free Electron Laser with up to 40 parameters while satisfying safe operation constraints.
Tasks
Published	2019-02-08
URL	https://arxiv.org/abs/1902.03229v2
PDF	https://arxiv.org/pdf/1902.03229v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-and-safe-bayesian-optimization-in
Repo	https://github.com/jkirschner42/LineBO
Framework	none