April 2, 2020

3476 words 17 mins read

Paper Group ANR 132

PanNuke Dataset Extension, Insights and Baselines. Efficient exploration of zero-sum stochastic games. Statistical Learning with Conditional Value at Risk. DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network. Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Reco …

PanNuke Dataset Extension, Insights and Baselines


Title	PanNuke Dataset Extension, Insights and Baselines
Authors	Jevgenij Gamper, Navid Alemi Koohbanani, Simon Graham, Mostafa Jahanifar, Syed Ali Khurram, Ayesha Azam, Katherine Hewitt, Nasir Rajpoot
Abstract	The emerging area of computational pathology (CPath) is ripe ground for the application of deep learning (DL) methods to healthcare due to the sheer volume of raw pixel data in whole-slide images (WSIs) of cancerous tissue slides. However, it is imperative for the DL algorithms relying on nuclei-level details to be able to cope with data from `the clinical wild’, which tends to be quite challenging. We study, and extend recently released PanNuke dataset consisting of ~200,000 nuclei categorized into 5 clinically important classes for the challenging tasks of segmenting and classifying nuclei in WSIs. Previous pan-cancer datasets consisted of only up to 9 different tissues and up to 21,000 unlabeled nuclei and just over 24,000 labeled nuclei with segmentation masks. PanNuke consists of 19 different tissue types that have been semi-automatically annotated and quality controlled by clinical pathologists, leading to a dataset with statistics similar to the clinical wild and with minimal selection bias. We study the performance of segmentation and classification models when applied to the proposed dataset and demonstrate the application of models trained on PanNuke to whole-slide images. We provide comprehensive statistics about the dataset and outline recommendations and research directions to address the limitations of existing DL tools when applied to real-world CPath applications. \|
Tasks
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10778v3
PDF	https://arxiv.org/pdf/2003.10778v3.pdf
PWC	https://paperswithcode.com/paper/pannuke-dataset-extension-insights-and
Repo
Framework

Efficient exploration of zero-sum stochastic games


Title	Efficient exploration of zero-sum stochastic games
Authors	Carlos Martin, Tuomas Sandholm
Abstract	We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay, such as in financial or military simulations and computer games. During a limited-duration learning phase, the algorithm can control the actions of both players in order to try to learn the game and how to play it well. After that, the algorithm has to produce a strategy that has low exploitability. Our motivation is to quickly learn strategies that have low exploitability in situations where evaluating the payoffs of a queried strategy profile is costly. For the stochastic game setting, we propose using the distribution of state-action value functions induced by a belief distribution over possible environments. We compare the performance of various exploration strategies for this task, including generalizations of Thompson sampling and Bayes-UCB to this new setting. These two consistently outperform other strategies.
Tasks	Efficient Exploration
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10524v1
PDF	https://arxiv.org/pdf/2002.10524v1.pdf
PWC	https://paperswithcode.com/paper/efficient-exploration-of-zero-sum-stochastic
Repo
Framework

Statistical Learning with Conditional Value at Risk


Title	Statistical Learning with Conditional Value at Risk
Authors	Tasuku Soma, Yuichi Yoshida
Abstract	We propose a risk-averse statistical learning framework wherein the performance of a learning algorithm is evaluated by the conditional value-at-risk (CVaR) of losses rather than the expected loss. We devise algorithms based on stochastic gradient descent for this framework. While existing studies of CVaR optimization require direct access to the underlying distribution, our algorithms make a weaker assumption that only i.i.d.\ samples are given. For convex and Lipschitz loss functions, we show that our algorithm has $O(1/\sqrt{n})$-convergence to the optimal CVaR, where $n$ is the number of samples. For nonconvex and smooth loss functions, we show a generalization bound on CVaR. By conducting numerical experiments on various machine learning tasks, we demonstrate that our algorithms effectively minimize CVaR compared with other baseline algorithms.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.05826v1
PDF	https://arxiv.org/pdf/2002.05826v1.pdf
PWC	https://paperswithcode.com/paper/statistical-learning-with-conditional-value
Repo
Framework


Title	DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network
Authors	Qiong Wu, Muhong Wu, Xu Chen, Zhi Zhou, Kaiwen He, Liang Chen
Abstract	Online social networks (OSNs) are emerging as the most popular mainstream platform for content cascade diffusion. In order to provide satisfactory quality of experience (QoE) for users in OSNs, much research dedicates to proactive content placement by using the propagation pattern, user’s personal profiles and social relationships in open social network scenarios (e.g., Twitter and Weibo). In this paper, we take a new direction of popularity-aware content placement in a closed social network (e.g., WeChat Moment) where user’s privacy is highly enhanced. We propose a novel data-driven holistic deep learning framework, namely DeepCP, for joint diffusion-aware cascade prediction and autonomous content placement without utilizing users’ personal and social information. We first devise a time-window LSTM model for content popularity prediction and cascade geo-distribution estimation. Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users’ QoE. We conduct extensive experiments using cascade diffusion traces in WeChat Moment (WM). Evaluation results corroborate that the proposed DeepCP framework can predict the content popularity with a high accuracy, generate efficient placement decision in a real-time manner, and achieve significant content access latency reduction over existing schemes.
Tasks	Decision Making
Published	2020-03-09
URL	https://arxiv.org/abs/2003.03971v1
PDF	https://arxiv.org/pdf/2003.03971v1.pdf
PWC	https://paperswithcode.com/paper/deepcp-deep-learning-driven-cascade
Repo
Framework

Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records


Title	Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records
Authors	Yikuan Li, Shishir Rao, Abdelaali Hassaine, Rema Ramakrishnan, Yajie Zhu, Dexter Canoy, Gholamreza Salimi-Khorshidi, Thomas Lukasiewicz, Kazem Rahimi
Abstract	One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks and sparse Gaussian processes are the main two scalable uncertainty estimation methods. However, deep Bayesian neural network suffers from lack of expressiveness, and more expressive models such as deep kernel learning, which is an extension of sparse Gaussian process, captures only the uncertainty from the higher level latent space. Therefore, the deep learning model under it lacks interpretability and ignores uncertainty from the raw data. In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for more comprehensive uncertainty estimation. Through a series of experiments on predicting the first incidence of heart failure, diabetes and depression applied to large-scale electronic medical records, we demonstrate that our method is better at capturing uncertainty than both Gaussian processes and deep Bayesian neural networks in terms of indicating data insufficiency and distinguishing true positive and false positive predictions, with a comparable generalisation performance. Furthermore, by assessing the accuracy and area under the receiver operating characteristic curve over the predictive probability, we show that our method is less susceptible to making overconfident predictions, especially for the minority class in imbalanced datasets. Finally, we demonstrate how uncertainty information derived by the model can inform risk factor analysis towards model interpretability.
Tasks	Decision Making, Gaussian Processes
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10170v1
PDF	https://arxiv.org/pdf/2003.10170v1.pdf
PWC	https://paperswithcode.com/paper/deep-bayesian-gaussian-processes-for
Repo
Framework

Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning


Title	Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning
Authors	Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres, Alessando L. Koerich, Claudine Badue, Alberto F. De Souza, Thiago Oliveira-Santos
Abstract	The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly relevant for supporting forensic investigation as documents may contain criminal evidence. As an alternative to the laborious and time-consuming manual process, several researchers have been investigating ways to perform automatic digital reconstruction. A central problem in automatic reconstruction of shredded documents is the pairwise compatibility evaluation of the shreds, notably for binary text documents. In this context, deep learning has enabled great progress for accurate reconstructions in the domain of mechanically-shredded documents. A sensitive issue, however, is that current deep model solutions require an inference whenever a pair of shreds has to be evaluated. This work proposes a scalable deep learning approach for measuring pairwise compatibility in which the number of inferences scales linearly (rather than quadratically) with the number of shreds. Instead of predicting compatibility directly, deep models are leveraged to asymmetrically project the raw shred content onto a common metric space in which distance is proportional to the compatibility. Experimental results show that our method has accuracy comparable to the state-of-the-art with a speed-up of about 22 times for a test instance with 505 shreds (20 mixed shredded-pages from different documents).
Tasks	Metric Learning
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10063v3
PDF	https://arxiv.org/pdf/2003.10063v3.pdf
PWC	https://paperswithcode.com/paper/faster-reconstruction-of-shredded-text
Repo
Framework

On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities


Title	On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities
Authors	Geoffrey Pettet, Ayan Mukhopadhyay, Mykel Kochenderfer, Yevgeniy Vorobeychik, Abhishek Dubey
Abstract	Emergency Response Management (ERM) is a critical problem faced by communities across the globe. Despite this, it is common for ERM systems to follow myopic decision policies in the real world. Principled approaches to aid ERM decision-making under uncertainty have been explored but have failed to be accepted into real systems. We identify a key issue impeding their adoption — algorithmic approaches to emergency response focus on reactive, post-incident dispatching actions, i.e. optimally dispatching a responder \textit{after} incidents occur. However, the critical nature of emergency response dictates that when an incident occurs, first responders always dispatch the closest available responder to the incident. We argue that the crucial period of planning for ERM systems is not post-incident, but between incidents. This is not a trivial planning problem — a major challenge with dynamically balancing the spatial distribution of responders is the complexity of the problem. An orthogonal problem in ERM systems is planning under limited communication, which is particularly important in disaster scenarios that affect communication networks. We address both problems by proposing two partially decentralized multi-agent planning algorithms that utilize heuristics and exploit the structure of the dispatch problem. We evaluate our proposed approach using real-world data, and find that in several contexts, dynamic re-balancing the spatial distribution of emergency responders reduces both the average response time as well as its variance.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07362v3
PDF	https://arxiv.org/pdf/2001.07362v3.pdf
PWC	https://paperswithcode.com/paper/on-algorithmic-decision-procedures-in
Repo
Framework

GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction


Title	GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction
Authors	Chengxin Wang, Shaofeng Cai, Gary Tan
Abstract	Trajectory prediction is a fundamental and challenging task to forecast the future path of the agents in autonomous applications with multi-agent interaction, where the agents need to predict the future movements of their neighbors to avoid collisions. To respond timely and precisely to the environment, high efficiency and accuracy are required in the prediction. Conventional approaches, e.g., LSTM-based models, take considerable computation costs in the prediction, especially for the long sequence prediction. To support a more efficient and accurate trajectory prediction, we instead propose a novel CNN-based spatial-temporal graph framework GraphTCN, which captures the spatial and temporal interactions in an input-aware manner. The spatial interaction between agents at each time step is captured with an edge graph attention network (EGAT), and the temporal interaction across time step is modeled with a modified gated convolutional network (CNN). In contrast to conventional models, both the spatial and temporal modeling in GraphTCN are computed within each local time window. Therefore, GraphTCN can be executed in parallel for much higher efficiency, and meanwhile with accuracy comparable to best-performing approaches. Experimental results confirm that GraphTCN achieves noticeably better performance in terms of both efficiency and accuracy compared with state-of-the-art methods on various trajectory prediction benchmark datasets.
Tasks	Trajectory Prediction
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07167v3
PDF	https://arxiv.org/pdf/2003.07167v3.pdf
PWC	https://paperswithcode.com/paper/graphtcn-spatio-temporal-interaction-modeling
Repo
Framework

Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray


Title	Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray
Authors	Weinan Song, Yuan Liang, Kun Wang, Lei He
Abstract	Panoramic X-ray and Cone Beam Computed Tomography (CBCT) are two of the most general imaging methods in digital dentistry. While CBCT can provide higher-dimension information, the panoramic X-ray has the advantages of lower radiation dose and cost. Consequently, generating 3D information of bony tissues from the X-ray that can reflect dental diseases is of great interest. This technique can be even more helpful for developing areas where the CBCT is not always available due to the lack of screening machines or high screening cost. In this paper, we present \textit{Oral-3D} to reconstruct the bone structure of oral cavity from a single panoramic X-ray image by taking advantage of some prior knowledge in oral structure, which conventionally can only be obtained by a 3D imaging method like CBCT. Specifically, we first train a generative network to back project the 2D X-ray image into 3D space, then restore the bone structure by registering the generated 3D image with the prior shape of the dental arch. To be noted, \textit{Oral-3D} can restore both the density of bony tissues and the curved mandible surface. Experimental results show that our framework can reconstruct the 3D structure with significantly high quality. To the best of our knowledge, this is the first work that explores 3D reconstruction from a 2D image in dental health.
Tasks	3D Reconstruction
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08413v2
PDF	https://arxiv.org/pdf/2003.08413v2.pdf
PWC	https://paperswithcode.com/paper/oral-3d-reconstructing-the-3d-bone-structure
Repo
Framework

Revisiting “Over-smoothing” in Deep GCNs


Title	Revisiting “Over-smoothing” in Deep GCNs
Authors	Chaoqi Yang, Ruijie Wang, Shuochao Yao, Shengzhong Liu, Tarek Abdelzaher
Abstract	Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). The evidence is usually derived from Simple Graph Convolution (SGC), a linear variant of GCNs. In this paper, we revisit graph node classification from an optimization perspective and argue that GCNs can actually learn anti-oversmoothing, whereas overfitting is the real obstacle in deep GCNs. This work interprets GCNs and SGCs as two-step optimization problems and provides the reason why deep SGC suffers from oversmoothing but deep GCNs do not. Our conclusion is compatible with the previous understanding of SGC, but we clarify why the same reasoning does not apply to GCNs. Based on our formulation, we provide more insights into the convolution operator and further propose a mean-subtraction trick to accelerate the training of deep GCNs. We verify our theory and propositions on three graph benchmarks. The experiments show that (i) in GCN, overfitting leads to the performance drop and oversmoothing does not exist even model goes to very deep (100 layers); (ii) mean-subtraction speeds up the model convergence as well as retains the same expressive power; (iii) the weight of neighbor averaging (1 is the common setting) does not significantly affect the model performance once it is above the threshold (> 0.5).
Tasks	Node Classification
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13663v1
PDF	https://arxiv.org/pdf/2003.13663v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-over-smoothing-in-deep-gcns
Repo
Framework

Automatic Section Recognition in Obituaries


Title	Automatic Section Recognition in Obituaries
Authors	Valentino Sabbatino, Laura Bostan, Roman Klinger
Abstract	Obituaries contain information about people’s values across times and cultures, which makes them a useful resource for exploring cultural history. They are typically structured similarly, with sections corresponding to Personal Information, Biographical Sketch, Characteristics, Family, Gratitude, Tribute, Funeral Information and Other aspects of the person. To make this information available for further studies, we propose a statistical model which recognizes these sections. To achieve that, we collect a corpus of 20058 English obituaries from TheDaily Item, Remembering.CA and The London Free Press. The evaluation of our annotation guidelines with three annotators on 1008 obituaries shows a substantial agreement of Fleiss k = 0.87. Formulated as an automatic segmentation task, a convolutional neural network outperforms bag-of-words and embedding-based BiLSTMs and BiLSTM-CRFs with a micro F1 = 0.81.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12699v1
PDF	https://arxiv.org/pdf/2002.12699v1.pdf
PWC	https://paperswithcode.com/paper/automatic-section-recognition-in-obituaries
Repo
Framework

From Perspective X-ray Imaging to Parallax-Robust Orthographic Stitching


Title	From Perspective X-ray Imaging to Parallax-Robust Orthographic Stitching
Authors	Javad Fotouhi, Xingtong Liu, Mehran Armand, Nassir Navab, Mathias Unberath
Abstract	Stitching images acquired under perspective projective geometry is a relevant topic in computer vision with multiple applications ranging from smartphone panoramas to the construction of digital maps. Image stitching is an equally prominent challenge in medical imaging, where the limited field-of-view captured by single images prohibits holistic analysis of patient anatomy. The barrier that prevents straight-forward mosaicing of 2D images is depth mismatch due to parallax. In this work, we leverage the Fourier slice theorem to aggregate information from multiple transmission images in parallax-free domains using fundamental principles of X-ray image formation. The semantics of the stitched image are restored using a novel deep learning strategy that exploits similarity measures designed around frequency, as well as dense and sparse spatial image content. Our pipeline, not only stitches images, but also provides orthographic reconstruction that enables metric measurements of clinically relevant quantities directly on the 2D image plane.
Tasks	Image Stitching
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02959v1
PDF	https://arxiv.org/pdf/2003.02959v1.pdf
PWC	https://paperswithcode.com/paper/from-perspective-x-ray-imaging-to-parallax
Repo
Framework

A Constraint Driven Solution Model for Discrete Domains with a Case Study of Exam Timetabling Problems


Title	A Constraint Driven Solution Model for Discrete Domains with a Case Study of Exam Timetabling Problems
Authors	Anuraganand Sharma
Abstract	Many science and engineering applications require finding solutions to planning and optimization problems by satisfying a set of constraints. These constraint problems (CPs) are typically NP-complete and can be formalized as constraint satisfaction problems (CSPs) or constraint optimization problems (COPs). Evolutionary algorithms (EAs) are good solvers for optimization problems ubiquitous in various problem domains, however traditional operators for EAs are ‘blind’ to constraints or generally use problem dependent objective functions; as they do not exploit information from the constraints in search for solutions. A variation of EA, Intelligent constraint handling evolutionary algorithm (ICHEA), has been demonstrated to be a versatile constraints-guided EA for continuous constrained problems in our earlier works in (Sharma and Sharma, 2012) where it extracts information from constraints and exploits it in the evolutionary search to make the search more efficient. In this paper ICHEA has been demonstrated to solve benchmark exam timetabling problems, a classic COP. The presented approach demonstrates competitive results with other state-of-the-art approaches in EAs in terms of quality of solutions. ICHEA first uses its inter-marriage crossover operator to satisfy all the given constraints incrementally and then uses combination of traditional and enhanced operators to optimize the solution. Generally CPs solved by EAs are problem dependent penalty based fitness functions. We also proposed a generic preference based solution model that does not require a problem dependent fitness function, however currently it only works for mutually exclusive constraints.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03102v1
PDF	https://arxiv.org/pdf/2002.03102v1.pdf
PWC	https://paperswithcode.com/paper/a-constraint-driven-solution-model-for
Repo
Framework

Invariant Causal Prediction for Block MDPs


Title	Invariant Causal Prediction for Block MDPs
Authors	Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
Abstract	Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider the problem of learning abstractions that generalize in block MDPs, families of environments with a shared latent state space and dynamics structure over that latent space, but varying observations. We leverage tools from causal inference to propose a method of invariant prediction to learn model-irrelevance state abstractions (MISA) that generalize to novel observations in the multi-environment setting. We prove that for certain classes of environments, this approach outputs with high probability a state abstraction corresponding to the causal feature set with respect to the return. We further provide more general bounds on model error and generalization error in the multi-environment setting, in the process showing a connection between causal variable selection and the state abstraction framework for MDPs. We give empirical evidence that our methods work in both linear and nonlinear settings, attaining improved generalization over single- and multi-task baselines.
Tasks	Causal Inference
Published	2020-03-12
URL	https://arxiv.org/abs/2003.06016v1
PDF	https://arxiv.org/pdf/2003.06016v1.pdf
PWC	https://paperswithcode.com/paper/invariant-causal-prediction-for-block-mdps
Repo
Framework

Safe Mission Planning under Dynamical Uncertainties


Title	Safe Mission Planning under Dynamical Uncertainties
Authors	Yimeng Lu, Maryam Kamgarpour
Abstract	This paper considers safe robot mission planning in uncertain dynamical environments. This problem arises in applications such as surveillance, emergency rescue, and autonomous driving. It is a challenging problem due to modeling and integrating dynamical uncertainties into a safe planning framework, and finding a solution in a computationally tractable way. In this work, we first develop a probabilistic model for dynamical uncertainties. Then, we provide a framework to generate a path that maximizes safety for complex missions by incorporating the uncertainty model. We also devise a Monte Carlo method to obtain a safe path efficiently. Finally, we evaluate the performance of our approach and compare it to potential alternatives in several case studies.
Tasks	Autonomous Driving
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02913v1
PDF	https://arxiv.org/pdf/2003.02913v1.pdf
PWC	https://paperswithcode.com/paper/safe-mission-planning-under-dynamical
Repo
Framework