February 2, 2020

3144 words 15 mins read

Paper Group AWR 70

Does My Rebuttal Matter? Insights from a Major NLP Conference. Capacity, Bandwidth, and Compositionality in Emergent Language Learning. On the Vulnerability of Capsule Networks to Adversarial Attacks. Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation. The Role of Embedding Complexity in …

Does My Rebuttal Matter? Insights from a Major NLP Conference


Title	Does My Rebuttal Matter? Insights from a Major NLP Conference
Authors	Yang Gao, Steffen Eger, Ilia Kuznetsov, Iryna Gurevych, Yusuke Miyao
Abstract	Peer review is a core element of the scientific process, particularly in conference-centered fields such as ML and NLP. However, only few studies have evaluated its properties empirically. Aiming to fill this gap, we present a corpus that contains over 4k reviews and 1.2k author responses from ACL-2018. We quantitatively and qualitatively assess the corpus. This includes a pilot study on paper weaknesses given by reviewers and on quality of author responses. We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i.e., final) scores from initial reviews and author responses. Although author responses do have a marginal (and statistically significant) influence on the final scores, especially for borderline papers, our results suggest that a reviewer’s final score is largely determined by her initial score and the distance to the other reviewers’ initial scores. In this context, we discuss the conformity bias inherent to peer reviewing, a bias that has largely been overlooked in previous research. We hope our analyses will help better assess the usefulness of the rebuttal phase in NLP conferences.
Tasks
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11367v2
PDF	http://arxiv.org/pdf/1903.11367v2.pdf
PWC	https://paperswithcode.com/paper/does-my-rebuttal-matter-insights-from-a-major
Repo	https://github.com/UKPLab/naacl2019-does-my-rebuttal-matter
Framework	none

Capacity, Bandwidth, and Compositionality in Emergent Language Learning


Title	Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Authors	Cinjon Resnick, Abhinav Gupta, Jakob Foerster, Andrew M. Dai, Kyunghyun Cho
Abstract	Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on communicative bandwidth as being of primary importance. While important, it is not the only contributing factor. In this paper, we investigate the learning biases that affect the efficacy and compositionality of emergent languages. Our foremost contribution is to explore how capacity of a neural network impacts its ability to learn a compositional language. We additionally introduce a set of evaluation metrics with which we analyze the learned languages. Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization. While we empirically see evidence for the bottom of this range, we curiously do not find evidence for the top part of the range and believe that this is an open question for the community.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11424v2
PDF	https://arxiv.org/pdf/1910.11424v2.pdf
PWC	https://paperswithcode.com/paper/capacity-bandwidth-and-compositionality-in
Repo	https://github.com/backpropper/cbc-emecom
Framework	pytorch

On the Vulnerability of Capsule Networks to Adversarial Attacks


Title	On the Vulnerability of Capsule Networks to Adversarial Attacks
Authors	Felix Michels, Tobias Uelwer, Eric Upschulte, Stefan Harmeling
Abstract	This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adversarial attacks than other neural networks. However, our experiments show that capsule networks can be fooled as easily as convolutional neural networks.
Tasks
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03612v1
PDF	https://arxiv.org/pdf/1906.03612v1.pdf
PWC	https://paperswithcode.com/paper/on-the-vulnerability-of-capsule-networks-to
Repo	https://github.com/felixmichels/Adversarial-Attacks-on-CapsNets
Framework	tf

Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation


Title	Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Authors	Hao Tang, Dan Xu, Yan Yan, Philip H. S. Torr, Nicu Sebe
Abstract	In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global image-level generation methods. To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes, and is able to provide more scene details. To learn more discriminative class-specific feature representations for the local generation, a novel classification module is also proposed. To combine the advantage of both the global image-level and the local class-specific generation, a joint generation network is designed with an attention fusion module and a dual-discriminator structure embedded. Extensive experiments on two scene image generation tasks show superior generation performance of the proposed model. The state-of-the-art results are established by large margins on both tasks and on challenging public benchmarks. The source code and trained models are available at https://github.com/Ha0Tang/LGGAN.
Tasks	Image Generation, Scene Generation
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12215v3
PDF	https://arxiv.org/pdf/1912.12215v3.pdf
PWC	https://paperswithcode.com/paper/local-class-specific-and-global-image-level
Repo	https://github.com/Ha0Tang/LocalGlobalGAN
Framework	none

The Role of Embedding Complexity in Domain-invariant Representations


Title	The Role of Embedding Complexity in Domain-invariant Representations
Authors	Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka
Abstract	Unsupervised domain adaptation aims to generalize the hypothesis trained in a source domain to an unlabeled target domain. One popular approach to this problem is to learn domain-invariant embeddings for both domains. In this work, we study, theoretically and empirically, the effect of the embedding complexity on generalization to the target domain. In particular, this complexity affects an upper bound on the target risk; this is reflected in experiments, too. Next, we specify our theoretical framework to multilayer neural networks. As a result, we develop a strategy that mitigates sensitivity to the embedding complexity, and empirically achieves performance on par with or better than the best layer-dependent complexity tradeoff.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05804v1
PDF	https://arxiv.org/pdf/1910.05804v1.pdf
PWC	https://paperswithcode.com/paper/the-role-of-embedding-complexity-in-domain-1
Repo	https://github.com/chingyaoc/mdm
Framework	pytorch

TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification


Title	TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification
Authors	Ahmed Shifaz, Charlotte Pelletier, Francois Petitjean, Geoffrey I. Webb
Abstract	Time Series Classification (TSC) has seen enormous progress over the last two decades. HIVE-COTE (Hierarchical Vote Collective of Transformation-based Ensembles) is the current state of the art in terms of classification accuracy. HIVE-COTE recognizes that time series data are a specific data type for which the traditional attribute-value representation, used predominantly in machine learning, fails to provide a relevant representation. HIVE-COTE combines multiple types of classifiers: each extracting information about a specific aspect of a time series, be it in the time domain, frequency domain or summarization of intervals within the series. However, HIVE-COTE (and its predecessor, FLAT-COTE) is often infeasible to run on even modest amounts of data. For instance, training HIVE-COTE on a dataset with only 1,500 time series can require 8 days of CPU time. It has polynomial runtime with respect to the training set size, so this problem compounds as data quantity increases. We propose a novel TSC algorithm, TS-CHIEF (Time Series Combination of Heterogeneous and Integrated Embedding Forest), which rivals HIVE-COTE in accuracy but requires only a fraction of the runtime. TS-CHIEF constructs an ensemble classifier that integrates the most effective embeddings of time series that research has developed in the last decade. It uses tree-structured classifiers to do so efficiently. We assess TS-CHIEF on 85 datasets of the University of California Riverside (UCR) archive, where it achieves state-of-the-art accuracy with scalability and efficiency. We demonstrate that TS-CHIEF can be trained on 130k time series in 2 days, a data quantity that is beyond the reach of any TSC algorithm with comparable accuracy.
Tasks	Time Series, Time Series Classification
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10329v2
PDF	https://arxiv.org/pdf/1906.10329v2.pdf
PWC	https://paperswithcode.com/paper/ts-chief-a-scalable-and-accurate-forest
Repo	https://github.com/dotnet54/TS-CHIEF
Framework	none

Adversarial $α$-divergence Minimization for Bayesian Approximate Inference


Title	Adversarial $α$-divergence Minimization for Bayesian Approximate Inference
Authors	Simón Rodríguez Santana, Daniel Hernández-Lobato
Abstract	Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good performance in many applications, it cannot easily output an estimate of the uncertainty in the predictions made. Estimating the uncertainty in the predictions is a critical aspect with important applications, and one method to obtain this information is following a Bayesian approach to estimate a posterior distribution on the model parameters. This posterior distribution summarizes which parameter values are compatible with the data, but is usually intractable and has to be approximated. Several mechanisms have been considered for solving this problem. We propose here a general method for approximate Bayesian inference that is based on minimizing{\alpha}-divergences and that allows for flexible approximate distributions. The method is evaluated in the context of Bayesian neural networks on extensive experiments. The results show that, in regression problems, it often gives better performance in terms of the test log-likelihoodand sometimes in terms of the squared error. In classification problems, however, it gives competitive results.
Tasks	Bayesian Inference
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06945v3
PDF	https://arxiv.org/pdf/1909.06945v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-divergence-minimization-for
Repo	https://github.com/simonrsantana/AADM
Framework	tf

RoadTagger: Robust Road Attribute Inference with Graph Neural Networks


Title	RoadTagger: Robust Road Attribute Inference with Graph Neural Networks
Authors	Songtao He, Favyen Bastani, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Samuel Madden, Mohammad Amin Sadeghi
Abstract	Inferring road attributes such as lane count and road type from satellite imagery is challenging. Often, due to the occlusion in satellite imagery and the spatial correlation of road attributes, a road attribute at one position on a road may only be apparent when considering far-away segments of the road. Thus, to robustly infer road attributes, the model must integrate scattered information and capture the spatial correlation of features along roads. Existing solutions that rely on image classifiers fail to capture this correlation, resulting in poor accuracy. We find this failure is caused by a fundamental limitation – the limited effective receptive field of image classifiers. To overcome this limitation, we propose RoadTagger, an end-to-end architecture which combines both Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs) to infer road attributes. The usage of graph neural networks allows information propagation on the road network graph and eliminates the receptive field limitation of image classifiers. We evaluate RoadTagger on both a large real-world dataset covering 688 km^2 area in 20 U.S. cities and a synthesized micro-dataset. In the evaluation, RoadTagger improves inference accuracy over the CNN image classifier based approaches. RoadTagger also demonstrates strong robustness against different disruptions in the satellite imagery and the ability to learn complicated inductive rules for aggregating scattered information along the road network.
Tasks
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12408v1
PDF	https://arxiv.org/pdf/1912.12408v1.pdf
PWC	https://paperswithcode.com/paper/roadtagger-robust-road-attribute-inference
Repo	https://github.com/mitroadmaps/roadtagger
Framework	tf

Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation


Title	Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation
Authors	Fernando Navarro, Suprosanna Shit, Ivan Ezhov, Johannes Paetzold, Andrei Gafita, Jan Peeken, Stephanie Combs, Bjoern Menze
Abstract	Multi-organ segmentation in whole-body computed tomography (CT) is a constant pre-processing step which finds its application in organ-specific image retrieval, radiotherapy planning, and interventional image analysis. We address this problem from an organ-specific shape-prior learning perspective. We introduce the idea of complementary-task learning to enforce shape-prior leveraging the existing target labels. We propose two complementary-tasks namely i) distance map regression and ii) contour map detection to explicitly encode the geometric properties of each organ. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans of multiple organs. We report a significant improvement of overall dice score from 0.8849 to 0.9018 due to the incorporation of complementary-task learning.
Tasks	Computed Tomography (CT), Image Retrieval
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05099v1
PDF	https://arxiv.org/pdf/1908.05099v1.pdf
PWC	https://paperswithcode.com/paper/shape-aware-complementary-task-learning-for
Repo	https://github.com/ferchonavarro/shape_aware_segmentation
Framework	tf

Callisto: Entropy based test generation and data quality assessment for Machine Learning Systems


Title	Callisto: Entropy based test generation and data quality assessment for Machine Learning Systems
Authors	Sakshi Udeshi, Xingbin Jiang, Sudipta Chattopadhyay
Abstract	Machine Learning (ML) has seen massive progress in the last decade and as a result, there is a pressing need for validating ML-based systems. To this end, we propose, design and evaluate CALLISTO - a novel test generation and data quality assessment framework. To the best of our knowledge, CALLISTO is the first blackbox framework to leverage the uncertainty in the prediction and systematically generate new test cases for ML classifiers. Our evaluation of CALLISTO on four real world data sets reveals thousands of errors. We also show that leveraging the uncertainty in prediction can increase the number of erroneous test cases up to a factor of 20, as compared to when no such knowledge is used for testing. CALLISTO has the capability to detect low quality data in the datasets that may contain mislabelled data. We conduct and present an extensive user study to validate the results of CALLISTO on identifying low quality data from four state-of-the-art real world datasets.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.08920v1
PDF	https://arxiv.org/pdf/1912.08920v1.pdf
PWC	https://paperswithcode.com/paper/callisto-entropy-based-test-generation-and
Repo	https://github.com/sakshiudeshi/Callisto
Framework	tf

Deep Active Inference as Variational Policy Gradients


Title	Deep Active Inference as Variational Policy Gradients
Authors	Beren Millidge
Abstract	Active Inference is a theory of action arising from neuroscience which casts action and planning as a bayesian inference problem to be solved by minimizing a single quantity - the variational free energy. Active Inference promises a unifying account of action and perception coupled with a biologically plausible process theory. Despite these potential advantages, current implementations of Active Inference can only handle small, discrete policy and state-spaces and typically require the environmental dynamics to be known. In this paper we propose a novel deep Active Inference algorithm which approximates key densities using deep neural networks as flexible function approximators, which enables Active Inference to scale to significantly larger and more complex tasks. We demonstrate our approach on a suite of OpenAIGym benchmark tasks and obtain performance comparable with common reinforcement learning baselines. Moreover, our algorithm shows similarities with maximum entropy reinforcement learning and the policy gradients algorithm, which reveals interesting connections between the Active Inference framework and reinforcement learning.
Tasks	Bayesian Inference
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03876v1
PDF	https://arxiv.org/pdf/1907.03876v1.pdf
PWC	https://paperswithcode.com/paper/deep-active-inference-as-variational-policy
Repo	https://github.com/Bmillidgework/DeepActiveInference_Code
Framework	none

Lung Nodule Classification using Deep Local-Global Networks


Title	Lung Nodule Classification using Deep Local-Global Networks
Authors	Mundher Al-Shabi, Boon Leong Lan, Wai Yee Chan, Kwan-Hoong Ng, Maxine Tan
Abstract	Purpose: Lung nodules have very diverse shapes and sizes, which makes classifying them as benign/malignant a challenging problem. In this paper, we propose a novel method to predict the malignancy of nodules that have the capability to analyze the shape and size of a nodule using a global feature extractor, as well as the density and structure of the nodule using a local feature extractor. Methods: We propose to use Residual Blocks with a 3x3 kernel size for local feature extraction, and Non-Local Blocks to extract the global features. The Non-Local Block has the ability to extract global features without using a huge number of parameters. The key idea behind the Non-Local Block is to apply matrix multiplications between features on the same feature maps. Results: We trained and validated the proposed method on the LIDC-IDRI dataset which contains 1,018 computed tomography (CT) scans. We followed a rigorous procedure for experimental setup namely, 10-fold cross-validation and ignored the nodules that had been annotated by less than 3 radiologists. The proposed method achieved state-of-the-art results with AUC=95.62%, while significantly outperforming other baseline methods. Conclusions: Our proposed Deep Local-Global network has the capability to accurately extract both local and global features. Our new method outperforms state-of-the-art architecture including Densenet and Resnet with transfer learning.
Tasks	Computed Tomography (CT), Lung Nodule Classification, Transfer Learning
Published	2019-04-23
URL	http://arxiv.org/abs/1904.10126v1
PDF	http://arxiv.org/pdf/1904.10126v1.pdf
PWC	https://paperswithcode.com/paper/lung-nodule-classification-using-deep-local
Repo	https://github.com/mundher/local-global
Framework	pytorch

Relation Adversarial Network for Low Resource Knowledge Graph Completion


Title	Relation Adversarial Network for Low Resource Knowledge Graph Completion
Authors	Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoayan Chen, Wei Zhang, Huajun Chen
Abstract	Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.
Tasks	Domain Adaptation, Knowledge Graph Completion, Knowledge Graphs, Link Prediction, Partial Domain Adaptation, Relation Extraction
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03091v4
PDF	https://arxiv.org/pdf/1911.03091v4.pdf
PWC	https://paperswithcode.com/paper/relation-adversarial-network-for-low-resource
Repo	https://github.com/zxlzr/RAN
Framework	none

Compact Trilinear Interaction for Visual Question Answering


Title	Compact Trilinear Interaction for Visual Question Answering
Authors	Tuong Do, Thanh-Toan Do, Huy Tran, Erman Tjiputra, Quang D. Tran
Abstract	In Visual Question Answering (VQA), answers have a great correlation with question meaning and visual contents. Thus, to selectively utilize image, question and answer information, we propose a novel trilinear interaction model which simultaneously learns high level associations between these three inputs. In addition, to overcome the interaction complexity, we introduce a multimodal tensor-based PARALIND decomposition which efficiently parameterizes trilinear interaction between the three inputs. Moreover, knowledge distillation is first time applied in Free-form Opened-ended VQA. It is not only for reducing the computational cost and required memory but also for transferring knowledge from trilinear interaction model to bilinear interaction model. The extensive experiments on benchmarking datasets TDIUC, VQA-2.0, and Visual7W show that the proposed compact trilinear interaction model achieves state-of-the-art results when using a single model on all three datasets.
Tasks	Question Answering, Visual Question Answering
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11874v1
PDF	https://arxiv.org/pdf/1909.11874v1.pdf
PWC	https://paperswithcode.com/paper/compact-trilinear-interaction-for-visual
Repo	https://github.com/aioz-ai/ICCV19_VQA-CTI
Framework	pytorch

An Annotated Dataset of Coreference in English Literature


Title	An Annotated Dataset of Coreference in English Literature
Authors	David Bamman, Olivia Lewke, Anya Mansoor
Abstract	We present in this work a new dataset of coreference annotations for works of literature in English, covering 29,104 mentions in 210,532 tokens from 100 works of fiction published between 1719 and 1922. This dataset differs from previous coreference corpora in containing documents whose average length (2,105.3 words) is four times longer than other benchmark datasets (463.7 for OntoNotes), and contains examples of difficult coreference problems common in literature. This dataset allows for an evaluation of cross-domain performance for the task of coreference resolution, and analysis into the characteristics of long-distance within-document coreference.
Tasks	Coreference Resolution
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01140v1
PDF	https://arxiv.org/pdf/1912.01140v1.pdf
PWC	https://paperswithcode.com/paper/an-annotated-dataset-of-coreference-in
Repo	https://github.com/dbamman/litbank
Framework	pytorch