April 2, 2020

3328 words 16 mins read

Paper Group ANR 157

Fill in the BLANC: Human-free quality estimation of document summaries. Linguistically Driven Graph Capsule Network for Visual Question Reasoning. RSVQA: Visual Question Answering for Remote Sensing Data. A Novel Fuzzy Approximate Reasoning Method Based on Extended Distance Measure in SISO Fuzzy System. Personalized Federated Learning: A Meta-Learn …

Fill in the BLANC: Human-free quality estimation of document summaries


Title	Fill in the BLANC: Human-free quality estimation of document summaries
Authors	Oleg Vasilyev, Vedant Dharnidharka, John Bohannon
Abstract	We present BLANC, a new approach to the automatic estimation of document summary quality. Our goal is to measure the functional performance of a summary with an objective, reproducible, and fully automated method. Our approach achieves this by measuring the performance boost gained by a pre-trained language model with access to a document summary while carrying out its language understanding task on the document’s text. We present evidence that BLANC scores have at least as good correlation with human evaluations as do the ROUGE family of summary quality measurements. And unlike ROUGE, the BLANC method does not require human-written reference summaries, allowing for fully human-free summary quality estimation.
Tasks	Language Modelling
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09836v1
PDF	https://arxiv.org/pdf/2002.09836v1.pdf
PWC	https://paperswithcode.com/paper/fill-in-the-blanc-human-free-quality
Repo
Framework

Linguistically Driven Graph Capsule Network for Visual Question Reasoning


Title	Linguistically Driven Graph Capsule Network for Visual Question Reasoning
Authors	Qingxing Cao, Xiaodan Liang, Keze Wang, Liang Lin
Abstract	Recently, studies of visual question answering have explored various architectures of end-to-end networks and achieved promising results on both natural and synthetic datasets, which require explicitly compositional reasoning. However, it has been argued that these black-box approaches lack interpretability of results, and thus cannot perform well on generalization tasks due to overfitting the dataset bias. In this work, we aim to combine the benefits of both sides and overcome their limitations to achieve an end-to-end interpretable structural reasoning for general images without the requirement of layout annotations. Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the “Linguistically driven Graph Capsule Network”, where the compositional process is guided by the linguistic parse tree. Specifically, we bind each capsule in the lowest layer to bridge the linguistic embedding of a single word in the original question with visual evidence and then route them to the same capsule if they are siblings in the parse tree. This compositional process is achieved by performing inference on a linguistically driven conditional random field (CRF) and is performed across multiple graph capsule layers, which results in a compositional reasoning process inside a CNN. Experiments on the CLEVR dataset, CLEVR compositional generation test, and FigureQA dataset demonstrate the effectiveness and composition generalization ability of our end-to-end model.
Tasks	Question Answering, Visual Question Answering
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10065v1
PDF	https://arxiv.org/pdf/2003.10065v1.pdf
PWC	https://paperswithcode.com/paper/linguistically-driven-graph-capsule-network
Repo
Framework

RSVQA: Visual Question Answering for Remote Sensing Data


Title	RSVQA: Visual Question Answering for Remote Sensing Data
Authors	Sylvain Lobry, Diego Marcos, Jesse Murray, Devis Tuia
Abstract	This paper introduces the task of visual question answering for remote sensing data (RSVQA). Remote sensing images contain a wealth of information which can be useful for a wide range of tasks including land cover classification, object counting or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method introduced in this article, we built two datasets (using low and high resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task. We report the results obtained by applying a model based on Convolutional Neural Networks (CNNs) for the visual part and on a Recurrent Neural Network (RNN) for the natural language part to this task. The model is trained on the two datasets, yielding promising results in both cases.
Tasks	Object Counting, Question Answering, Visual Question Answering
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07333v1
PDF	https://arxiv.org/pdf/2003.07333v1.pdf
PWC	https://paperswithcode.com/paper/rsvqa-visual-question-answering-for-remote
Repo
Framework

A Novel Fuzzy Approximate Reasoning Method Based on Extended Distance Measure in SISO Fuzzy System


Title	A Novel Fuzzy Approximate Reasoning Method Based on Extended Distance Measure in SISO Fuzzy System
Authors	I. M. Son, S. I. Kwak, U. J. Han, J. H. Pak, M. Han, J. R. Pyon, U. S. Ryu
Abstract	This paper presents an original method of fuzzy approximate reasoning that can open a new direction of research in the uncertainty inference of Artificial Intelligence(AI) and Computational Intelligence(CI). Fuzzy modus ponens (FMP) and fuzzy modus tollens(FMT) are two fundamental and basic models of general fuzzy approximate reasoning in various fuzzy systems. And the reductive property is one of the essential and important properties in the approximate reasoning theory and it is a lot of applications. This paper suggests a kind of extended distance measure (EDM) based approximate reasoning method in the single input single output(SISO) fuzzy system with discrete fuzzy set vectors of different dimensions. The EDM based fuzzy approximate reasoning method is consists of two part, i.e., FMP-EDM and FMT-EDM. The distance measure based fuzzy reasoning method that the dimension of the antecedent discrete fuzzy set is equal to one of the consequent discrete fuzzy set has already solved in other paper. In this paper discrete fuzzy set vectors of different dimensions mean that the dimension of the antecedent discrete fuzzy set differs from one of the consequent discrete fuzzy set in the SISO fuzzy system. That is, this paper is based on EDM. The experimental results highlight that the proposed approximate reasoning method is comparatively clear and effective with respect to the reductive property, and in accordance with human thinking than existing fuzzy reasoning methods.
Tasks
Published	2020-03-27
URL	https://arxiv.org/abs/2003.13450v1
PDF	https://arxiv.org/pdf/2003.13450v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-fuzzy-approximate-reasoning-method
Repo
Framework

Personalized Federated Learning: A Meta-Learning Approach


Title	Personalized Federated Learning: A Meta-Learning Approach
Authors	Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar
Abstract	The goal of federated learning is to design algorithms in which several agents communicate with a central node, in a privacy-protecting manner, to minimize the average of their loss functions. In this approach, each node not only shares the required computational budget but also has access to a larger data set, which improves the quality of the resulting model. However, this method only develops a common output for all the agents, and therefore, does not adapt the model to each user data. This is an important missing feature especially given the heterogeneity of the underlying data distribution for various agents. In this paper, we study a personalized variant of the federated learning in which our goal is to find a shared initial model in a distributed manner that can be slightly updated by either a current or a new user by performing one or a few steps of gradient descent with respect to its own loss function. This approach keeps all the benefits of the federated learning architecture while leading to a more personalized model for each user. We show this problem can be studied within the Model-Agnostic Meta-Learning (MAML) framework. Inspired by this connection, we propose a personalized variant of the well-known Federated Averaging algorithm and evaluate its performance in terms of gradient norm for non-convex loss functions. Further, we characterize how this performance is affected by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.
Tasks	Meta-Learning
Published	2020-02-19
URL	https://arxiv.org/abs/2002.07948v1
PDF	https://arxiv.org/pdf/2002.07948v1.pdf
PWC	https://paperswithcode.com/paper/personalized-federated-learning-a-meta
Repo
Framework

Pruning Convolutional Neural Networks with Self-Supervision


Title	Pruning Convolutional Neural Networks with Self-Supervision
Authors	Mathilde Caron, Ari Morcos, Piotr Bojanowski, Julien Mairal, Armand Joulin
Abstract	Convolutional neural networks trained without supervision come close to matching performance with supervised pre-training, but sometimes at the cost of an even higher number of parameters. Extracting subnetworks from these large unsupervised convnets with preserved performance is of particular interest to make them less computationally intensive. Typical pruning methods operate during training on a task while trying to maintain the performance of the pruned network on the same task. However, in self-supervised feature learning, the training objective is agnostic on the representation transferability to downstream tasks. Thus, preserving performance for this objective does not ensure that the pruned subnetwork remains effective for solving downstream tasks. In this work, we investigate the use of standard pruning methods, developed primarily for supervised learning, for networks trained without labels (i.e. on self-supervised tasks). We show that pruned masks obtained with or without labels reach comparable performance when re-trained on labels, suggesting that pruning operates similarly for self-supervised and supervised learning. Interestingly, we also find that pruning preserves the transfer performance of self-supervised subnetwork representations.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03554v1
PDF	https://arxiv.org/pdf/2001.03554v1.pdf
PWC	https://paperswithcode.com/paper/pruning-convolutional-neural-networks-with
Repo
Framework

Detection in Crowded Scenes: One Proposal, Multiple Predictions


Title	Detection in Crowded Scenes: One Proposal, Multiple Predictions
Authors	Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, Jian Sun
Abstract	We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9% AP gains on challenging CrowdHuman dataset and 1.0% $\text{MR}^{-2}$ improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at https://github.com/megvii-model/CrowdDetection.
Tasks
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09163v1
PDF	https://arxiv.org/pdf/2003.09163v1.pdf
PWC	https://paperswithcode.com/paper/detection-in-crowded-scenes-one-proposal
Repo
Framework

Context-Aware Parse Trees


Title	Context-Aware Parse Trees
Authors	Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Paul Petersen, Jesmin Jahan Tithi, Tim Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich
Abstract	The simplified parse tree (SPT) presented in Aroma, a state-of-the-art code recommendation system, is a tree-structured representation used to infer code semantics by capturing program \emph{structure} rather than program \emph{syntax}. This is a departure from the classical abstract syntax tree, which is principally driven by programming language syntax. While we believe a semantics-driven representation is desirable, the specifics of an SPT’s construction can impact its performance. We analyze these nuances and present a new tree structure, heavily influenced by Aroma’s SPT, called a \emph{context-aware parse tree} (CAPT). CAPT enhances SPT by providing a richer level of semantic representation. Specifically, CAPT provides additional binding support for language-specific techniques for adding semantically-salient features, and language-agnostic techniques for removing syntactically-present but semantically-irrelevant features. Our research quantitatively demonstrates the value of our proposed semantically-salient features, enabling a specific CAPT configuration to be 39% more accurate than SPT across the 48,610 programs we analyzed.
Tasks
Published	2020-03-24
URL	https://arxiv.org/abs/2003.11118v1
PDF	https://arxiv.org/pdf/2003.11118v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-parse-trees
Repo
Framework

Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis


Title	Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
Authors	Roozbeh Yousefzadeh, Dianne P. O’Leary
Abstract	Deep learning models have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Nevertheless, they are consistently utilized in many applications, consequential to humans’ lives, mostly because of their better performance. Therefore, there is a great need for computational methods that can explain, audit, and debug such models. Here, we use flip points to accomplish these goals for deep learning models with continuous output scores (e.g., computed by softmax), used in social applications. A flip point is any point that lies on the boundary between two output classes: e.g. for a model with a binary yes/no output, a flip point is any input that generates equal scores for “yes” and “no”. The flip point closest to a given input is of particular importance because it reveals the least changes in the input that would change a model’s classification, and we show that it is the solution to a well-posed optimization problem. Flip points also enable us to systematically study the decision boundaries of a deep learning classifier. The resulting insight into the decision boundaries of a deep model can clearly explain the model’s output on the individual-level, via an explanation report that is understandable by non-experts. We also develop a procedure to understand and audit model behavior towards groups of people. Flip points can also be used to alter the decision boundaries in order to improve undesirable behaviors. We demonstrate our methods by investigating several models trained on standard datasets used in social applications of machine learning. We also identify the features that are most responsible for particular classifications and misclassifications.
Tasks
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00682v1
PDF	https://arxiv.org/pdf/2001.00682v1.pdf
PWC	https://paperswithcode.com/paper/auditing-and-debugging-deep-learning-models
Repo
Framework

Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting


Title	Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Authors	Zixin Zhong, Wang Chi Cheung, Vincent Y. F. Tan
Abstract	We design and analyze CascadeBAI, an algorithm for finding the best set of $K$ items, also called an arm, within the framework of cascading bandits. An upper bound on the time complexity of CascadeBAI is derived by overcoming a crucial analytical challenge, namely, that of probabilistically estimating the amount of available feedback at each step. To do so, we define a new class of random variables (r.v.‘s) which we term as left-sided sub-Gaussian r.v.‘s; these are r.v.‘s whose cumulant generating functions (CGFs) can be bounded by a quadratic only for non-positive arguments of the CGFs. This enables the application of a sufficiently tight Bernstein-type concentration inequality. We show, through the derivation of a lower bound on the time complexity, that the performance of CascadeBAI is optimal in some practical regimes. Finally, extensive numerical simulations corroborate the efficacy of CascadeBAI as well as the tightness of our upper bound on its time complexity.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08655v2
PDF	https://arxiv.org/pdf/2001.08655v2.pdf
PWC	https://paperswithcode.com/paper/best-arm-identification-for-cascading-bandits
Repo
Framework

FFR V1.0: Fon-French Neural Machine Translation


Title	FFR V1.0: Fon-French Neural Machine Translation
Authors	Bonaventure F. P. Dossou, Chris C. Emezue
Abstract	Africa has the highest linguistic diversity in the world. On account of the importance of language to communication, and the importance of reliable, powerful and accurate machine translation models in modern inter-cultural communication, there have been (and still are) efforts to create state-of-the-art translation models for the many African languages. However, the low-resources, diacritical and tonal complexities of African languages are major issues facing African NLP today. The FFR is a major step towards creating a robust translation model from Fon, a very low-resource and tonal language, to French, for research and public use. In this paper, we describe our pilot project: the creation of a large growing corpora for Fon-to-French translations and our FFR v1.0 model, trained on this dataset. The dataset and model are made publicly available.
Tasks	Machine Translation
Published	2020-03-26
URL	https://arxiv.org/abs/2003.12111v1
PDF	https://arxiv.org/pdf/2003.12111v1.pdf
PWC	https://paperswithcode.com/paper/ffr-v1-0-fon-french-neural-machine
Repo
Framework

Online Binary Space Partitioning Forests


Title	Online Binary Space Partitioning Forests
Authors	Xuhui Fan, Bin Li, Scott A. Sisson
Abstract	The Binary Space Partitioning-Tree~(BSP-Tree) process was recently proposed as an efficient strategy for space partitioning tasks. Because it uses more than one dimension to partition the space, the BSP-Tree Process is more efficient and flexible than conventional axis-aligned cutting strategies. However, due to its batch learning setting, it is not well suited to large-scale classification and regression problems. In this paper, we develop an online BSP-Forest framework to address this limitation. With the arrival of new data, the resulting online algorithm can simultaneously expand the space coverage and refine the partition structure, with guaranteed universal consistency for both classification and regression problems. The effectiveness and competitive performance of the online BSP-Forest is verified via simulations on real-world datasets.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00269v1
PDF	https://arxiv.org/pdf/2003.00269v1.pdf
PWC	https://paperswithcode.com/paper/online-binary-space-partitioning-forests
Repo
Framework

Non-Aligned Distribution Distance using Metric Measure Embedding and Optimal Transport


Title	Non-Aligned Distribution Distance using Metric Measure Embedding and Optimal Transport
Authors	Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso, Alain Rakotomamonjy
Abstract	We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance that compares pairwise distance of elements from each distribution, we consider a method that embeds the metric measure spaces in a common Euclidean space and computes an optimal transport (OT) on the embedded distributions. This leads to what we call a sub-embedding robust Wasserstein(SERW). Under some conditions, SERW is a distance that considers an OT distance of the (low-distorted) embedded distributions using a common metric. In addition to this novel proposal that generalizes several recent OT works, our contributions stand on several theoretical analyses: i) we characterize the embedding spaces to define SERW distance for distribution alignment; ii) we prove that SERW mimics almost the same properties of GW distance, and we give a cost relation between GW and SERW. The paper also provides some numerical experiments illustrating how SERW behaves on matching problems in real-world.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08314v1
PDF	https://arxiv.org/pdf/2002.08314v1.pdf
PWC	https://paperswithcode.com/paper/non-aligned-distribution-distance-using
Repo
Framework

Firms Default Prediction with Machine Learning


Title	Firms Default Prediction with Machine Learning
Authors	Tesi Aliaj, Aris Anagnostopoulos, Stefano Piersanti
Abstract	Academics and practitioners have studied over the years models for predicting firms bankruptcy, using statistical and machine-learning approaches. An earlier sign that a company has financial difficulties and may eventually bankrupt is going in \emph{default}, which, loosely speaking means that the company has been having difficulties in repaying its loans towards the banking system. Firms default status is not technically a failure but is very relevant for bank lending policies and often anticipates the failure of the company. Our study uses, for the first time according to our knowledge, a very large database of granular credit data from the Italian Central Credit Register of Bank of Italy that contain information on all Italian companies’ past behavior towards the entire Italian banking system to predict their default using machine-learning techniques. Furthermore, we combine these data with other information regarding companies’ public balance sheet data. We find that ensemble techniques and random forest provide the best results, corroborating the findings of Barboza et al. (Expert Syst. Appl., 2017).
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.11705v1
PDF	https://arxiv.org/pdf/2002.11705v1.pdf
PWC	https://paperswithcode.com/paper/firms-default-prediction-with-machine
Repo
Framework

ITeM: Independent Temporal Motifs to Summarize and Compare Temporal Networks


Title	ITeM: Independent Temporal Motifs to Summarize and Compare Temporal Networks
Authors	Sumit Purohit, Lawrence B. Holder, George Chin
Abstract	Networks are a fundamental and flexible way of representing various complex systems. Many domains such as communication, citation, procurement, biology, social media, and transportation can be modeled as a set of entities and their relationships. Temporal networks are a specialization of general networks where the temporal evolution of the system is as important to understand as the structure of the entities and relationships. We present the Independent Temporal Motif (ITeM) to characterize temporal graphs from different domains. The ITeMs are edge-disjoint temporal motifs that can be used to model the structure and the evolution of the graph. For a given temporal graph, we produce a feature vector of ITeM frequencies and apply this distribution to the task of measuring the similarity of temporal graphs. We show that ITeM has higher accuracy than other motif frequency-based approaches. We define various metrics based on ITeM that reveal salient properties of a temporal network. We also present importance sampling as a method for efficiently estimating the ITeM counts. We evaluate our approach on both synthetic and real temporal networks.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08312v1
PDF	https://arxiv.org/pdf/2002.08312v1.pdf
PWC	https://paperswithcode.com/paper/item-independent-temporal-motifs-to-summarize
Repo
Framework