January 26, 2020

3474 words 17 mins read

Paper Group ANR 1507

Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games. Forecasting the Progression of Alzheimer’s Disease Using Neural Networks and a Novel Pre-Processing Algorithm. On the Reliability of Cancelable Biometrics: Revisit the Irreversibility. Does computer vision matter for action?. Reducing the Human Effort in Developing PET- …

Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games


Title	Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games
Authors	Philip Bontrager, Ahmed Khalifa, Damien Anderson, Matthew Stephenson, Christoph Salge, Julian Togelius
Abstract	Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learning-based agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforcement learners, and that the resulting behavior highlights the shortcomings of the learning algorithm. The particular ways in which agents fail differ from how planning-based agents fail, further illuminating the character of these algorithms. We propose an initial typology of deceptions which could help us better understand pitfalls and failure modes of (deep) reinforcement learning.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04436v1
PDF	https://arxiv.org/pdf/1908.04436v1.pdf
PWC	https://paperswithcode.com/paper/superstition-in-the-network-deep
Repo
Framework

Forecasting the Progression of Alzheimer’s Disease Using Neural Networks and a Novel Pre-Processing Algorithm


Title	Forecasting the Progression of Alzheimer’s Disease Using Neural Networks and a Novel Pre-Processing Algorithm
Authors	Jack Albright
Abstract	Alzheimer’s disease (AD) is the most common neurodegenerative disease in older people. Despite considerable efforts to find a cure for AD, there is a 99.6% failure rate of clinical trials for AD drugs, likely because AD patients cannot easily be identified at early stages. This project investigated machine learning approaches to predict the clinical state of patients in future years to benefit AD research. Clinical data from 1737 patients was obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database and was processed using the “All-Pairs” technique, a novel methodology created for this project involving the comparison of all possible pairs of temporal data points for each patient. This data was then used to train various machine learning models. Models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset (110 patients). A neural network model was effective (mAUC = 0.866) at predicting the progression of AD on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment. Such a model could be used to identify patients at early stages of AD and who are therefore good candidates for clinical trials for AD therapeutics.
Tasks
Published	2019-03-18
URL	http://arxiv.org/abs/1903.07510v2
PDF	http://arxiv.org/pdf/1903.07510v2.pdf
PWC	https://paperswithcode.com/paper/forecasting-the-progression-of-alzheimers
Repo
Framework

On the Reliability of Cancelable Biometrics: Revisit the Irreversibility


Title	On the Reliability of Cancelable Biometrics: Revisit the Irreversibility
Authors	Xingbo Dong, Zhe Jin, Andrew Beng Jin Teoh, Massimo Tistarelli, KokSheik Wong
Abstract	Over the years, many biometric template protection schemes, primarily based on the notion of “cancelable biometrics” have been proposed. A cancelable biometric algorithm needs to satisfy four biometric template protection criteria, i.e., irreversibility, revocability, unlinkability, and performance preservation. However, a systematic analysis of irreversibility has been often neglected. In this paper, the common distance correlation characteristic of cancelable biometrics is analyzed. Next, a similarity-based attack is formulated to break the irreversibility of cancelable biometric under the Kerckhoffs’s assumption where the cancelable biometrics algorithm and parameter are known to the attackers. The irreversibility based on the mutual information is also redefined, and a framework to measure the information leakage from the distance correlation characteristic is proposed. The results achieved on face, iris, and fingerprint prove that it is theoretically hard to meet full irreversibility. To have a good biometric system, a balance has to be achieved between accuracy and security.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07770v2
PDF	https://arxiv.org/pdf/1910.07770v2.pdf
PWC	https://paperswithcode.com/paper/on-the-reliability-of-cancelable-biometrics
Repo
Framework

Does computer vision matter for action?


Title	Does computer vision matter for action?
Authors	Brady Zhou, Philipp Krähenbühl, Vladlen Koltun
Abstract	Computer vision produces representations of scene content. Much computer vision research is predicated on the assumption that these intermediate representations are useful for action. Recent work at the intersection of machine learning and robotics calls this assumption into question by training sensorimotor systems directly for the task at hand, from pixels to actions, with no explicit intermediate representations. Thus the central question of our work: Does computer vision matter for action? We probe this question and its offshoots via immersive simulation, which allows us to conduct controlled reproducible experiments at scale. We instrument immersive three-dimensional environments to simulate challenges such as urban driving, off-road trail traversal, and battle. Our main finding is that computer vision does matter. Models equipped with intermediate representations train faster, achieve higher task performance, and generalize better to previously unseen environments. A video that summarizes the work and illustrates the results can be found at https://youtu.be/4MfWa2yZ0Jc
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12887v2
PDF	https://arxiv.org/pdf/1905.12887v2.pdf
PWC	https://paperswithcode.com/paper/does-computer-vision-matter-for-action
Repo
Framework

Reducing the Human Effort in Developing PET-CT Registration


Title	Reducing the Human Effort in Developing PET-CT Registration
Authors	Teaghan O’Briain, Kyong Hwan Jin, Hongyoon Choi, Erika Chin, Magdalena Bazalova-Carter, Kwang Moo Yi
Abstract	We aim to reduce the tedious nature of developing and evaluating methods for aligning PET-CT scans from multiple patient visits. Current methods for registration rely on correspondences that are created manually by medical experts with 3D manipulation, or assisted alignments done by utilizing mutual information across CT scans that may not be consistent when transferred to the PET images. Instead, we propose to label multiple key points across several 2D slices, which we then fit a key curve to. This removes the need for creating manual alignments in 3D and makes the labelling process easier. We use these key curves to define an error metric for the alignments that can be computed efficiently. While our metric is non-differentiable, we further show that we can utilize it during the training of our deep model via a novel method. Specifically, instead of relying on detailed geometric labels – e.g., manual 3D alignments – we use synthetically generated deformations of real data. To incorporate robustness to changes that occur between visits other than geometric changes, we enforce consistency across visits in the deep network’s internal representations. We demonstrate the potential of our method via qualitative and quantitative experiments.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10657v1
PDF	https://arxiv.org/pdf/1911.10657v1.pdf
PWC	https://paperswithcode.com/paper/reducing-the-human-effort-in-developing-pet
Repo
Framework

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases


Title	DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
Authors	Zhiqing Sun, Jian Tang, Pan Du, Zhi-Hong Deng, Jian-Yun Nie
Abstract	Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and recent neural network-based approaches. Specifically, given a document, a word graph is constructed from the document based on word proximity and is encoded with graph convolutional networks, which effectively capture document-level word salience by modeling long-range dependency between words in the document and aggregating multiple appearances of identical words into one node. Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process. Experimental results on five benchmark data sets show that our proposed method significantly outperforms the existing state-of-the-art approaches.
Tasks	Document Summarization, Information Retrieval
Published	2019-05-19
URL	https://arxiv.org/abs/1905.07689v1
PDF	https://arxiv.org/pdf/1905.07689v1.pdf
PWC	https://paperswithcode.com/paper/divgraphpointer-a-graph-pointer-network-for
Repo
Framework

Solving All Regression Models For Learning Gaussian Networks Using Givens Rotations


Title	Solving All Regression Models For Learning Gaussian Networks Using Givens Rotations
Authors	Borzou Alipourfard, Jean X. Gao
Abstract	Score based learning (SBL) is a promising approach for learning Bayesian networks. The initial step in the majority of the SBL algorithms consists of computing the scores of all possible child and parent-set combinations for the variables. For Bayesian networks with continuous variables, a particular score is usually calculated as a function of the regression of the child over the variables in the parent-set. The sheer number of regressions models to be solved necessitates the design of efficient numerical algorithms. In this paper, we propose an algorithm for an efficient and exact calculation of regressions for all child and parent-set combinations. In the proposed algorithm, we use QR decompositions (QRDs) to capture the dependencies between the regressions for different families and Givens rotations to efficiently traverse through the space of QRDs such that all the regression models are accounted for in the shortest path possible. We compare the complexity of the suggested method with different algorithms, mainly those arising in all subset regression problems, and show that our algorithm has the smallest algorithmic complexity. We also explain how to parallelize the proposed method so as to decrease the runtime by a factor proportional to the number of processors utilized.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07643v1
PDF	http://arxiv.org/pdf/1901.07643v1.pdf
PWC	https://paperswithcode.com/paper/solving-all-regression-models-for-learning
Repo
Framework

Multi-Graph Decoding for Code-Switching ASR


Title	Multi-Graph Decoding for Code-Switching ASR
Authors	Emre Yılmaz, Samuel Cohen, Xianghu Yue, David van Leeuwen, Haizhou Li
Abstract	In the FAME! Project, a code-switching (CS) automatic speech recognition (ASR) system for Frisian-Dutch speech is developed that can accurately transcribe the local broadcaster’s bilingual archives with CS speech. This archive contains recordings with monolingual Frisian and Dutch speech segments as well as Frisian-Dutch CS speech, hence the recognition performance on monolingual segments is also vital for accurate transcriptions. In this work, we propose a multi-graph decoding and rescoring strategy using bilingual and monolingual graphs together with a unified acoustic model for CS ASR. The proposed decoding scheme gives the freedom to design and employ alternative search spaces for each (monolingual or bilingual) recognition task and enables the effective use of monolingual resources of the high-resourced mixed language in low-resourced CS scenarios. In our scenario, Dutch is the high-resourced and Frisian is the low-resourced language. We therefore use additional monolingual Dutch text resources to improve the Dutch language model (LM) and compare the performance of single- and multi-graph CS ASR systems on Dutch segments using larger Dutch LMs. The ASR results show that the proposed approach outperforms baseline single-graph CS ASR systems, providing better performance on the monolingual Dutch segments without any accuracy loss on monolingual Frisian and code-mixed segments.
Tasks	Language Modelling, Speech Recognition
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07523v2
PDF	https://arxiv.org/pdf/1906.07523v2.pdf
PWC	https://paperswithcode.com/paper/multi-graph-decoding-for-code-switching-asr
Repo
Framework

CHAMELEON: A Deep Learning Meta-Architecture for News Recommender Systems [Phd. Thesis]


Title	CHAMELEON: A Deep Learning Meta-Architecture for News Recommender Systems [Phd. Thesis]
Authors	Gabriel de Souza Pereira Moreira
Abstract	Recommender Systems (RS) have became a popular research topic and, since 2016, Deep Learning methods and techniques have been increasingly explored in this area. News RS are aimed to personalize users experiences and help them discover relevant articles from a large and dynamic search space. The main contribution of this research was named CHAMELEON, a Deep Learning meta-architecture designed to tackle the specific challenges of news recommendation. It consists of a modular reference architecture which can be instantiated using different neural building blocks. As information about users’ past interactions is scarce in the news domain, the user context can be leveraged to deal with the user cold-start problem. Articles’ content is also important to tackle the item cold-start problem. Additionally, the temporal decay of items (articles) relevance is very accelerated in the news domain. Furthermore, external breaking events may temporally attract global readership attention, a phenomenon generally known as concept drift in machine learning. All those characteristics are explicitly modeled on this research by a contextual hybrid session-based recommendation approach using Recurrent Neural Networks. The task addressed by this research is session-based news recommendation, i.e., next-click prediction using only information available in the current user session. A method is proposed for a realistic temporal offline evaluation of such task, replaying the stream of user clicks and fresh articles being continuously published in a news portal. Experiments performed with two large datasets have shown the effectiveness of the CHAMELEON for news recommendation on many quality factors such as accuracy, item coverage, novelty, and reduced item cold-start problem, when compared to other traditional and state-of-the-art session-based recommendation algorithms.
Tasks	Recommendation Systems, Session-Based Recommendations
Published	2019-12-29
URL	https://arxiv.org/abs/2001.04831v1
PDF	https://arxiv.org/pdf/2001.04831v1.pdf
PWC	https://paperswithcode.com/paper/chameleon-a-deep-learning-meta-architecture
Repo
Framework

DIVE: A spatiotemporal progression model of brain pathology in neurodegenerative disorders


Title	DIVE: A spatiotemporal progression model of brain pathology in neurodegenerative disorders
Authors	Razvan V. Marinescu, Arman Eshaghi, Marco Lorenzi, Alexandra L. Young, Neil P. Oxtoby, Sara Garbarino, Sebastian J. Crutch, Daniel C. Alexander
Abstract	Here we present DIVE: Data-driven Inference of Vertexwise Evolution. DIVE is an image-based disease progression model with single-vertex resolution, designed to reconstruct long-term patterns of brain pathology from short-term longitudinal data sets. DIVE clusters vertex-wise biomarker measurements on the cortical surface that have similar temporal dynamics across a patient population, and concurrently estimates an average trajectory of vertex measurements in each cluster. DIVE uniquely outputs a parcellation of the cortex into areas with common progression patterns, leading to a new signature for individual diseases. DIVE further estimates the disease stage and progression speed for every visit of every subject, potentially enhancing stratification for clinical trials or management. On simulated data, DIVE can recover ground truth clusters and their underlying trajectory, provided the average trajectories are sufficiently different between clusters. We demonstrate DIVE on data from two cohorts: the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Dementia Research Centre (DRC), UK, containing patients with Posterior Cortical Atrophy (PCA) as well as typical Alzheimer’s disease (tAD). DIVE finds similar spatial patterns of atrophy for tAD subjects in the two independent datasets (ADNI and DRC), and further reveals distinct patterns of pathology in different diseases (tAD vs PCA) and for distinct types of biomarker data: cortical thickness from Magnetic Resonance Imaging (MRI) vs amyloid load from Positron Emission Tomography (PET). Finally, DIVE can be used to estimate a fine-grained spatial distribution of pathology in the brain using any kind of voxelwise or vertexwise measures including Jacobian compression maps, fractional anisotropy (FA) maps from diffusion imaging or other PET measures. DIVE source code is available online: https://github.com/mrazvan22/dive
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03553v1
PDF	http://arxiv.org/pdf/1901.03553v1.pdf
PWC	https://paperswithcode.com/paper/dive-a-spatiotemporal-progression-model-of
Repo
Framework

Understanding the (un)interpretability of natural image distributions using generative models


Title	Understanding the (un)interpretability of natural image distributions using generative models
Authors	Ryen Krusinga, Sohil Shah, Matthias Zwicker, Tom Goldstein, David Jacobs
Abstract	Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensional image distributions. More recent generative models leverage the power of neural networks to implicitly learn and represent probability models over complex images. We describe methods to extract explicit probability density estimates from GANs, and explore the properties of these image density functions. We perform sanity check experiments to provide evidence that these probabilities are reasonable. However, we also show that density functions of natural images are difficult to interpret and thus limited in use. We study reasons for this lack of interpretability, and show that we can get interpretability back by doing density estimation on latent representations of images.
Tasks	Density Estimation
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01499v2
PDF	http://arxiv.org/pdf/1901.01499v2.pdf
PWC	https://paperswithcode.com/paper/understanding-the-uninterpretability-of
Repo
Framework

Gated Graph Convolutional Recurrent Neural Networks


Title	Gated Graph Convolutional Recurrent Neural Networks
Authors	Luana Ruiz, Fernando Gama, Alejandro Ribeiro
Abstract	Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems. GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered. We also put forward Gated GCRNNs, a time-gated variation of GCRNNs akin to LSTMs. When compared with GNNs and another graph recurrent architecture in experiments using both synthetic and real-word data, GCRNNs significantly improve performance while using considerably less parameters.
Tasks	Node Classification
Published	2019-03-05
URL	https://arxiv.org/abs/1903.01888v3
PDF	https://arxiv.org/pdf/1903.01888v3.pdf
PWC	https://paperswithcode.com/paper/gated-graph-convolutional-recurrent-neural
Repo
Framework

On assumption-free tests and confidence intervals for causal effects estimated by machine learning


Title	On assumption-free tests and confidence intervals for causal effects estimated by machine learning
Authors	Lin Liu, Rajarshi Mukherjee, James M Robins
Abstract	For many causal effect parameters $\psi$ of interest doubly robust machine learning estimators $\widehat\psi_1$ are the state-of-the-art, incorporating the benefits of the low prediction error of machine learning algorithms; the decreased bias of doubly robust estimators; and.the analytic tractability and bias reduction of cross fitting. When the potential confounders is high dimensional, the associated $(1 - \alpha)$ Wald intervals may still undercover even in large samples, because the bias may be of the same or even larger order than its standard error. In this paper, we introduce tests that can have the power to detect whether the bias of $\widehat\psi_1$ is of the same or even larger order than its standard error of order $n^{-1/2}$, can provide a lower confidence limit on the degree of under coverage of the interval and strikingly, are valid under essentially no assumptions. We also introduce an estimator with bias generally less than that of $\widehat\psi_1$, yet whose standard error is not much greater than $\widehat\psi_1$'s. The tests, as well as the estimator $\widehat\psi_2$, are based on a U-statistic that is the second-order influence function for the parameter that encodes the estimable part of the bias of $\widehat\psi_1$. Our impressive claims need to be tempered in several important ways. First no test, including ours, of the null hypothesis that the ratio of the bias to its standard error can be consistent [without making additional assumptions that may be incorrect]. Furthermore the above claims only apply to parameters in a particular class. For the others, our results are less sharp and require more careful interpretation.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04276v1
PDF	http://arxiv.org/pdf/1904.04276v1.pdf
PWC	https://paperswithcode.com/paper/on-assumption-free-tests-and-confidence
Repo
Framework

Deep Conversational Recommender in Travel


Title	Deep Conversational Recommender in Travel
Authors	Lizi Liao, Ryuichi Takanobu, Yunshan Ma, Xun Yang, Minlie Huang, Tat-Seng Chua
Abstract	When traveling to a foreign country, we are often in dire need of an intelligent conversational agent to provide instant and informative responses to our various queries. However, to build such a travel agent is non-trivial. First of all, travel naturally involves several sub-tasks such as hotel reservation, restaurant recommendation and taxi booking etc, which invokes the need for global topic control. Secondly, the agent should consider various constraints like price or distance given by the user to recommend an appropriate venue. In this paper, we present a Deep Conversational Recommender (DCR) and apply to travel. It augments the sequence-to-sequence (seq2seq) models with a neural latent topic component to better guide response generation and make the training easier. To consider the various constraints for venue recommendation, we leverage a graph convolutional network (GCN) based approach to capture the relationships between different venues and the match between venue and dialog context. For response generation, we combine the topic-based component with the idea of pointer networks, which allows us to effectively incorporate recommendation results. We perform extensive evaluation on a multi-turn task-oriented dialog dataset in travel domain and the results show that our method achieves superior performance as compared to a wide range of baselines.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1907.00710v1
PDF	https://arxiv.org/pdf/1907.00710v1.pdf
PWC	https://paperswithcode.com/paper/deep-conversational-recommender-in-travel
Repo
Framework

Happiness Entailment: Automating Suggestions for Well-Being


Title	Happiness Entailment: Automating Suggestions for Well-Being
Authors	Sara Evensen, Yoshihiko Suhara, Alon Halevy, Vivian Li, Wang-Chiew Tan, Saran Mumick
Abstract	Understanding what makes people happy is a central topic in psychology. Prior work has mostly focused on developing self-reporting assessment tools for individuals and relies on experts to analyze the periodic reported assessments. One of the goals of the analysis is to understand what actions are necessary to encourage modifications in the behaviors of the individuals to improve their overall well-being. In this paper, we outline a complementary approach; on the assumption that the user journals her happy moments as short texts, a system can analyze these texts and propose sustainable suggestions for the user that may lead to an overall improvement in her well-being. We prototype one necessary component of such a system, the Happiness Entailment Recognition (HER) module, which takes as input a short text describing an event, a candidate suggestion, and outputs a determination about whether the suggestion is more likely to be good for this user based on the event described. This component is implemented as a neural network model with two encoders, one for the user input and one for the candidate actionable suggestion, with additional layers to capture psychologically significant features in the happy moment and suggestion.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10036v1
PDF	https://arxiv.org/pdf/1907.10036v1.pdf
PWC	https://paperswithcode.com/paper/happiness-entailment-automating-suggestions
Repo
Framework