January 31, 2020

3414 words 17 mins read

Paper Group ANR 149

NEAR: Neighborhood Edge AggregatoR for Graph Classification. Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings. Answering Questions about Data Visualizations using Efficient Bimodal Fusion. SIMPLE: Statistical Inference on Membership Profiles in Large Networks. Stochastic One-Sided Full-Information Bandi …

NEAR: Neighborhood Edge AggregatoR for Graph Classification


Title	NEAR: Neighborhood Edge AggregatoR for Graph Classification
Authors	Cheolhyeong Kim, Haeseong Moon, Hyung Ju Hwang
Abstract	Learning graph-structured data with graph neural networks (GNNs) has been recently emerging as an important field because of its wide applicability in bioinformatics, chemoinformatics, social network analysis and data mining. Recent GNN algorithms are based on neural message passing, which enables GNNs to integrate local structures and node features recursively. However, past GNN algorithms based on 1-hop neighborhood neural message passing are exposed to a risk of loss of information on local structures and relationships. In this paper, we propose Neighborhood Edge AggregatoR (NEAR), a novel framework that aggregates relations between the nodes in the neighborhood via edges. NEAR, which can be orthogonally combined with previous GNN algorithms, gives integrated information that describes which nodes in the neighborhood are connected. Therefore, GNNs combined with NEAR reflect each node’s local structure beyond the nodes themselves. Experimental results on multiple graph classification tasks show that our algorithm achieves state-of-the-art results.
Tasks	Graph Classification
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02746v1
PDF	https://arxiv.org/pdf/1909.02746v1.pdf
PWC	https://paperswithcode.com/paper/near-neighborhood-edge-aggregator-for-graph
Repo
Framework

Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings


Title	Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
Authors	Tom Everitt, Pedro A. Ortega, Elizabeth Barnes, Shane Legg
Abstract	Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction using causal influence diagrams, we can answer two fundamental questions about an agent’s incentives directly from the graph: (1) which nodes can the agent have an incentivize to observe, and (2) which nodes can the agent have an incentivize to control? The answers tell us which information and influence points need extra protection. For example, we may want a classifier for job applications to not use the ethnicity of the candidate, and a reinforcement learning agent not to take direct control of its reward mechanism. Different algorithms and training paradigms can lead to different causal influence diagrams, so our method can be used to identify algorithms with problematic incentives and help in designing algorithms with better incentives.
Tasks
Published	2019-02-26
URL	https://arxiv.org/abs/1902.09980v6
PDF	https://arxiv.org/pdf/1902.09980v6.pdf
PWC	https://paperswithcode.com/paper/understanding-agent-incentives-using-causal
Repo
Framework

Answering Questions about Data Visualizations using Efficient Bimodal Fusion


Title	Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Authors	Kushal Kafle, Robik Shrestha, Brian Price, Scott Cohen, Christopher Kanan
Abstract	Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie charts, and line graphs. CQA requires capabilities that natural-image VQA algorithms lack: fine-grained measurements, optical character recognition, and handling out-of-vocabulary words in both questions and answers. Without modifications, state-of-the-art VQA algorithms perform poorly on this task. Here, we propose a novel CQA algorithm called parallel recurrent fusion of image and language (PReFIL). PReFIL first learns bimodal embeddings by fusing question and image features and then intelligently aggregates these learned embeddings to answer the given question. Despite its simplicity, PReFIL greatly surpasses state-of-the art systems and human baselines on both the FigureQA and DVQA datasets. Additionally, we demonstrate that PReFIL can be used to reconstruct tables by asking a series of questions about a chart.
Tasks	Optical Character Recognition, Question Answering, Visual Question Answering
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01801v1
PDF	https://arxiv.org/pdf/1908.01801v1.pdf
PWC	https://paperswithcode.com/paper/answering-questions-about-data-visualizations
Repo
Framework

SIMPLE: Statistical Inference on Membership Profiles in Large Networks


Title	SIMPLE: Statistical Inference on Membership Profiles in Large Networks
Authors	Jianqing Fan, Yingying Fan, Xiao Han, Jinchi Lv
Abstract	Network data is prevalent in many contemporary big data applications in which a common interest is to unveil important latent links between different pairs of nodes. Yet a simple fundamental question of how to precisely quantify the statistical uncertainty associated with the identification of latent links still remains largely unexplored. In this paper, we propose the method of statistical inference on membership profiles in large networks (SIMPLE) in the setting of degree-corrected mixed membership model, where the null hypothesis assumes that the pair of nodes share the same profile of community memberships. In the simpler case of no degree heterogeneity, the model reduces to the mixed membership model for which an alternative more robust test is also proposed. Both tests are of the Hotelling-type statistics based on the rows of empirical eigenvectors or their ratios, whose asymptotic covariance matrices are very challenging to derive and estimate. Nevertheless, their analytical expressions are unveiled and the unknown covariance matrices are consistently estimated. Under some mild regularity conditions, we establish the exact limiting distributions of the two forms of SIMPLE test statistics under the null hypothesis and contiguous alternative hypothesis. They are the chi-square distributions and the noncentral chi-square distributions, respectively, with degrees of freedom depending on whether the degrees are corrected or not. We also address the important issue of estimating the unknown number of communities and establish the asymptotic properties of the associated test statistics. The advantages and practical utility of our new procedures in terms of both size and power are demonstrated through several simulation examples and real network applications.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01734v1
PDF	https://arxiv.org/pdf/1910.01734v1.pdf
PWC	https://paperswithcode.com/paper/simple-statistical-inference-on-membership
Repo
Framework

Stochastic One-Sided Full-Information Bandit


Title	Stochastic One-Sided Full-Information Bandit
Authors	Haoyu Zhao, Wei Chen
Abstract	In this paper, we study the stochastic version of the one-sided full information bandit problem, where we have $K$ arms $[K] = {1, 2, \ldots, K}$, and playing arm $i$ would gain reward from an unknown distribution for arm $i$ while obtaining reward feedback for all arms $j \ge i$. One-sided full information bandit can model the online repeated second-price auctions, where the auctioneer could select the reserved price in each round and the bidders only reveal their bids when their bids are higher than the reserved price. In this paper, we present an elimination-based algorithm to solve the problem. Our elimination based algorithm achieves distribution independent regret upper bound $O(\sqrt{T\cdot\log (TK)})$, and distribution dependent bound $O((\log T + \log K)f(\Delta))$, where $T$ is the time horizon, $\Delta$ is a vector of gaps between the mean reward of arms and the mean reward of the best arm, and $f(\Delta)$ is a formula depending on the gap vector that we will specify in detail. Our algorithm has the best theoretical regret upper bound so far. We also validate our algorithm empirically against other possible alternatives.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08656v1
PDF	https://arxiv.org/pdf/1906.08656v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-one-sided-full-information-bandit
Repo
Framework

LEAF-QA: Locate, Encode & Attend for Figure Question Answering


Title	LEAF-QA: Locate, Encode & Attend for Figure Question Answering
Authors	Ritwick Chaudhry, Sumit Shekhar, Utkarsh Gupta, Pranav Maneriker, Prann Bansal, Ajay Joshi
Abstract	We introduce LEAF-QA, a comprehensive dataset of $250,000$ densely annotated figures/charts, constructed from real-world open data sources, along with ~2 million question-answer (QA) pairs querying the structure and semantics of these charts. LEAF-QA highlights the problem of multimodal QA, which is notably different from conventional visual QA (VQA), and has recently gained interest in the community. Furthermore, LEAF-QA is significantly more complex than previous attempts at chart QA, viz. FigureQA and DVQA, which present only limited variations in chart data. LEAF-QA being constructed from real-world sources, requires a novel architecture to enable question answering. To this end, LEAF-Net, a deep architecture involving chart element localization, question and answer encoding in terms of chart elements, and an attention network is proposed. Different experiments are conducted to demonstrate the challenges of QA on LEAF-QA. The proposed architecture, LEAF-Net also considerably advances the current state-of-the-art on FigureQA and DVQA.
Tasks	Question Answering, Visual Question Answering
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12861v1
PDF	https://arxiv.org/pdf/1907.12861v1.pdf
PWC	https://paperswithcode.com/paper/leaf-qa-locate-encode-attend-for-figure
Repo
Framework

Netherlands Dataset: A New Public Dataset for Machine Learning in Seismic Interpretation


Title	Netherlands Dataset: A New Public Dataset for Machine Learning in Seismic Interpretation
Authors	Reinaldo Mozart Silva, Lais Baroni, Rodrigo S. Ferreira, Daniel Civitarese, Daniela Szwarcman, Emilio Vital Brazil
Abstract	Machine learning and, more specifically, deep learning algorithms have seen remarkable growth in their popularity and usefulness in the last years. This is arguably due to three main factors: powerful computers, new techniques to train deeper networks and larger datasets. Although the first two are readily available in modern computers and ML libraries, the last one remains a challenge for many domains. It is a fact that big data is a reality in almost all fields nowadays, and geosciences are not an exception. However, to achieve the success of general-purpose applications such as ImageNet - for which there are +14 million labeled images for 1000 target classes - we not only need more data, we need more high-quality labeled data. When it comes to the Oil&Gas industry, confidentiality issues hamper even more the sharing of datasets. In this work, we present the Netherlands interpretation dataset, a contribution to the development of machine learning in seismic interpretation. The Netherlands F3 dataset acquisition was carried out in the North Sea, Netherlands offshore. The data is publicly available and contains pos-stack data, 8 horizons and well logs of 4 wells. For the purposes of our machine learning tasks, the original dataset was reinterpreted, generating 9 horizons separating different seismic facies intervals. The interpreted horizons were used to generate approximatelly 190,000 labeled images for inlines and crosslines. Finally, we present two deep learning applications in which the proposed dataset was employed and produced compelling results.
Tasks	Seismic Interpretation
Published	2019-03-26
URL	http://arxiv.org/abs/1904.00770v1
PDF	http://arxiv.org/pdf/1904.00770v1.pdf
PWC	https://paperswithcode.com/paper/netherlands-dataset-a-new-public-dataset-for
Repo
Framework

Specification-Driven Predictive Business Process Monitoring


Title	Specification-Driven Predictive Business Process Monitoring
Authors	Ario Santoso, Michael Felderer
Abstract	Predictive analysis in business process monitoring aims at forecasting the future information of a running business process. The prediction is typically made based on the model extracted from historical process execution logs (event logs). In practice, different business domains might require different kinds of predictions. Hence, it is important to have a means for properly specifying the desired prediction tasks, and a mechanism to deal with these various prediction tasks. Although there have been many studies in this area, they mostly focus on a specific prediction task. This work introduces a language for specifying the desired prediction tasks, and this language allows us to express various kinds of prediction tasks. This work also presents a mechanism for automatically creating the corresponding prediction model based on the given specification. Differently from previous studies, instead of focusing on a particular prediction task, we present an approach to deal with various prediction tasks based on the given specification of the desired prediction tasks. We also provide an implementation of the approach which is used to conduct experiments using real-life event logs.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1904.09422v1
PDF	http://arxiv.org/pdf/1904.09422v1.pdf
PWC	https://paperswithcode.com/paper/specification-driven-predictive-business
Repo
Framework

Selective Sensor Fusion for Neural Visual-Inertial Odometry


Title	Selective Sensor Fusion for Neural Visual-Inertial Odometry
Authors	Changhao Chen, Stefano Rosa, Yishu Miao, Chris Xiaoxuan Lu, Wei Wu, Andrew Markham, Niki Trigoni
Abstract	Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective sensor fusion framework for monocular VIO, which fuses monocular images and inertial measurements in order to estimate the trajectory whilst improving robustness to real-life issues, such as missing and corrupted data or bad sensor synchronization. In particular, we propose two fusion modalities based on different masking strategies: deterministic soft fusion and stochastic hard fusion, and we compare with previously proposed direct fusion baselines. During testing, the network is able to selectively process the features of the available sensor modalities and produce a trajectory at scale. We present a thorough investigation on the performances on three public autonomous driving, Micro Aerial Vehicle (MAV) and hand-held VIO datasets. The results demonstrate the effectiveness of the fusion strategies, which offer better performances compared to direct fusion, particularly in presence of corrupted data. In addition, we study the interpretability of the fusion networks by visualising the masking layers in different scenarios and with varying data corruption, revealing interesting correlations between the fusion networks and imperfect sensory input data.
Tasks	Autonomous Driving, Sensor Fusion
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01534v1
PDF	http://arxiv.org/pdf/1903.01534v1.pdf
PWC	https://paperswithcode.com/paper/selective-sensor-fusion-for-neural-visual
Repo
Framework

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales


Title	Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales
Authors	James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum
Abstract	This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from the image of rigidly-transformed coplanar features. The solvers work on scenes without straight lines and, in general, relax strong assumptions about scene content made by the state of the art. The proposed solvers use the affine invariant that coplanar repeats have the same scale in rectified space. The solvers are separated into two groups that differ by how the equal scale invariant of rectified space is used to place constraints on the lens undistortion and rectification parameters. We demonstrate a principled approach for generating stable minimal solvers by the Gr"obner basis method, which is accomplished by sampling feasible monomial bases to maximize numerical stability. Synthetic and real-image experiments confirm that the proposed solvers demonstrate superior robustness to noise compared to the state of the art. Accurate rectifications on imagery taken with narrow to fisheye field-of-view lenses demonstrate the wide applicability of the proposed method. The method is fully automatic.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.11539v1
PDF	https://arxiv.org/pdf/1907.11539v1.pdf
PWC	https://paperswithcode.com/paper/minimal-solvers-for-rectifying-from-radially
Repo
Framework

RLINK: Deep Reinforcement Learning for User Identity Linkage


Title	RLINK: Deep Reinforcement Learning for User Identity Linkage
Authors	Xiaoxue Li, Yanan Cao, Yanmin Shang, Yangxi Li, Yanbing Liu, Jianlong Tan
Abstract	User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting the label of identity pairs or selecting the most relevant identity pair based on the similarity scores. However, most of these methods ignore the results of previously matched identities, which could contribute to the linkage in following matching steps. To address this problem, we convert user identity linkage into a sequence decision problem and propose a reinforcement learning model to optimize the linkage strategy from the global perspective. Our method makes full use of both the social network structure and the history matched identities, and explores the long-term influence of current matching on subsequent decisions. We conduct experiments on different types of datasets, the results show that our method achieves better performance than other state-of-the-art methods.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14273v1
PDF	https://arxiv.org/pdf/1910.14273v1.pdf
PWC	https://paperswithcode.com/paper/rlink-deep-reinforcement-learning-for-user
Repo
Framework

IoT Notary: Sensor Data Attestation in Smart Environment


Title	IoT Notary: Sensor Data Attestation in Smart Environment
Authors	Nisha Panwar, Shantanu Sharma, Guoxi Wang, Sharad Mehrotra, Nalini Venkatasubramanian, Mamadou H. Diallo, Ardalan Amiri Sani
Abstract	Contemporary IoT environments, such as smart buildings, require end-users to trust data-capturing rules published by the systems. There are several reasons why such a trust is misplaced — IoT systems may violate the rules deliberately or IoT devices may transfer user data to a malicious third-party due to cyberattacks, leading to the loss of individuals’ privacy or service integrity. To address such concerns, we propose IoT Notary, a framework to ensure trust in IoT systems and applications. IoT Notary provides secure log sealing on live sensor data to produce a verifiable `proof-of-integrity,’ based on which a verifier can attest that captured sensor data adheres to the published data-capturing rules. IoT Notary is an integral part of TIPPERS, a smart space system that has been deployed at UCI to provide various real-time location-based services in the campus. IoT Notary imposes nominal overheads for verification, thereby users can verify their data of one day in less than two seconds. \|
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10033v1
PDF	https://arxiv.org/pdf/1908.10033v1.pdf
PWC	https://paperswithcode.com/paper/iot-notary-sensor-data-attestation-in-smart
Repo
Framework

Enforcing Reasoning in Visual Commonsense Reasoning


Title	Enforcing Reasoning in Visual Commonsense Reasoning
Authors	Hammad A. Ayyubi, Md. Mehrab Tanjim, David J. Kriegman
Abstract	The task of Visual Commonsense Reasoning is extremely challenging in the sense that the model has to not only be able to answer a question given an image, but also be able to learn to reason. The baselines introduced in this task are quite limiting because two networks are trained for predicting answers and rationales separately. Question and image is used as input to train answer prediction network while question, image and correct answer are used as input in the rationale prediction network. As rationale is conditioned on the correct answer, it is based on the assumption that we can solve Visual Question Answering task without any error - which is over ambitious. Moreover, such an approach makes both answer and rationale prediction two completely independent VQA tasks rendering cognition task meaningless. In this paper, we seek to address these issues by proposing an end-to-end trainable model which considers both answers and their reasons jointly. Specifically, we first predict the answer for the question and then use the chosen answer to predict the rationale. However, a trivial design of such a model becomes non-differentiable which makes it difficult to train. We solve this issue by proposing four approaches - softmax, gumbel-softmax, reinforcement learning based sampling and direct cross entropy against all pairs of answers and rationales. We demonstrate through experiments that our model performs competitively against current state-of-the-art. We conclude with an analysis of presented approaches and discuss avenues for further work.
Tasks	Question Answering, Visual Commonsense Reasoning, Visual Question Answering
Published	2019-10-21
URL	https://arxiv.org/abs/1910.11124v2
PDF	https://arxiv.org/pdf/1910.11124v2.pdf
PWC	https://paperswithcode.com/paper/enforcing-reasoning-in-visual-commonsense
Repo
Framework

CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion


Title	CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
Authors	Xinjing Cheng, Peng Wang, Chenye Guan, Ruigang Yang
Abstract	Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as “context-aware CSPN”, while weighted selection, “resource-aware CSPN” can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods.
Tasks	Depth Completion
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05377v2
PDF	https://arxiv.org/pdf/1911.05377v2.pdf
PWC	https://paperswithcode.com/paper/cspn-learning-context-and-resource-aware
Repo
Framework

Can Graph Neural Networks Help Logic Reasoning?


Title	Can Graph Neural Networks Help Logic Reasoning?
Authors	Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song
Abstract	Effectively combining logic reasoning and probabilistic inference has been a long-standing goal of machine learning: the former has the ability to generalize with small training data, while the latter provides a principled framework for dealing with noisy data. However, existing methods for combining the best of both worlds are typically computationally intensive. In this paper, we focus on Markov Logic Networks and explore the use of graph neural networks (GNNs) for representing probabilistic logic inference. It is revealed from our analysis that the representation power of GNN alone is not enough for such a task. We instead propose a more expressive variant, called ExpressGNN, which can perform effective probabilistic logic inference while being able to scale to a large number of entities. We demonstrate by several benchmark datasets that ExpressGNN has the potential to advance probabilistic logic reasoning to the next stage.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02111v3
PDF	https://arxiv.org/pdf/1906.02111v3.pdf
PWC	https://paperswithcode.com/paper/can-graph-neural-networks-help-logic
Repo
Framework