January 28, 2020

3319 words 16 mins read

Paper Group ANR 842

Investment Ranking Challenge: Identifying the best performing stocks based on their semi-annual returns. End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning. When is a Prediction Knowledge?. Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views. Dissecting Non-Vacuous Gene …

Investment Ranking Challenge: Identifying the best performing stocks based on their semi-annual returns


Title	Investment Ranking Challenge: Identifying the best performing stocks based on their semi-annual returns
Authors	Shanka Subhra Mondal, Sharada Prasanna Mohanty, Benjamin Harlander, Mehmet Koseoglu, Lance Rane, Kirill Romanov, Wei-Kai Liu, Pranoot Hatwar, Marcel Salathe, Joe Byrum
Abstract	In the IEEE Investment ranking challenge 2018, participants were asked to build a model which would identify the best performing stocks based on their returns over a forward six months window. Anonymized financial predictors and semi-annual returns were provided for a group of anonymized stocks from 1996 to 2017, which were divided into 42 non-overlapping six months period. The second half of 2017 was used as an out-of-sample test of the model’s performance. Metrics used were Spearman’s Rank Correlation Coefficient and Normalized Discounted Cumulative Gain (NDCG) of the top 20% of a model’s predicted rankings. The top six participants were invited to describe their approach. The solutions used were varied and were based on selecting a subset of data to train, combination of deep and shallow neural networks, different boosting algorithms, different models with different sets of features, linear support vector machine, combination of convoltional neural network (CNN) and Long short term memory (LSTM).
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08636v1
PDF	https://arxiv.org/pdf/1906.08636v1.pdf
PWC	https://paperswithcode.com/paper/investment-ranking-challenge-identifying-the
Repo
Framework

End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning


Title	End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
Authors	Fabian B. Fuchs, Adam R. Kosiorek, Li Sun, Oiwi Parker Jones, Ingmar Posner
Abstract	Relational reasoning - the ability to model interactions and relations between objects - is valuable for robust multi-object tracking and pivotal for trajectory prediction. In this paper, we propose MOHART, a class-agnostic, end-to-end multi-object tracking and trajectory prediction algorithm, which explicitly accounts for permutation invariance in its relational reasoning. We explore a number of permutation invariant architectures and show that multi-headed self-attention outperforms the provided baselines and better accounts for complex physical interactions in a challenging toy experiment. We show on three real-world tracking datasets that adding relational reasoning capabilities in this way increases the tracking and trajectory prediction performance, particularly in the presence of ego-motion, occlusions, crowded scenes, and faulty sensor inputs. To the best of our knowledge, MOHART is the first fully end-to-end multi-object tracking from vision approach applied to real-world data reported in the literature.
Tasks	Autonomous Vehicles, Multi-Object Tracking, Object Tracking, Relational Reasoning, Trajectory Prediction
Published	2019-07-12
URL	https://arxiv.org/abs/1907.12887v3
PDF	https://arxiv.org/pdf/1907.12887v3.pdf
PWC	https://paperswithcode.com/paper/end-to-end-recurrent-multi-object-tracking
Repo
Framework

When is a Prediction Knowledge?


Title	When is a Prediction Knowledge?
Authors	Alex Kearney, Patrick M. Pilarski
Abstract	Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent’s knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection of architectural proposals, but also as the beginnings of a theory of machine knowledge in reinforcement learning. Recent work has expanded what can be expressed using predictions, and developed applications which use predictions to inform decision-making on a variety of synthetic and real-world problems. While promising, we here suggest that the notion of predictions as knowledge in reinforcement learning is as yet underdeveloped: some work explicitly refers to predictions as knowledge, what the requirements are for considering a prediction to be knowledge have yet to be well explored. This specification of the necessary and sufficient conditions of knowledge is important; even if claims about the nature of knowledge are left implicit in technical proposals, the underlying assumptions of such claims have consequences for the systems we design. These consequences manifest in both the way we choose to structure predictive knowledge architectures, and how we evaluate them. In this paper, we take a first step to formalizing predictive knowledge by discussing the relationship of predictive knowledge learning methods to existing theories of knowledge in epistemology. Specifically, we explore the relationships between Generalized Value Functions and epistemic notions of Justification and Truth.
Tasks	Decision Making
Published	2019-04-18
URL	http://arxiv.org/abs/1904.09024v1
PDF	http://arxiv.org/pdf/1904.09024v1.pdf
PWC	https://paperswithcode.com/paper/when-is-a-prediction-knowledge
Repo
Framework

Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views


Title	Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
Authors	Anastasiia Doinychko, Massih-Reza Amini
Abstract	In this paper, we present a conditional GAN with two generators and a common discriminator for multiview learning problems where observations have two views, but one of them may be missing for some of the training samples. This is for example the case for multilingual collections where documents are not available in all languages. Some studies tackled this problem by assuming the existence of view generation functions to approximately complete the missing views; for example Machine Translation to translate documents into the missing languages. These functions generally require an external resource to be set and their quality has a direct impact on the performance of the learned multiview classifier over the completed training set. Our proposed approach addresses this problem by jointly learning the missing views and the multiview classifier using a tripartite game with two generators and a discriminator. Each of the generators is associated to one of the views and tries to fool the discriminator by generating the other missing view conditionally on the corresponding observed view. The discriminator then tries to identify if for an observation, one of its views is completed by one of the generators or if both views are completed along with its class. Our results on a subset of Reuters RCV1/RCV2 collections show that the discriminator achieves significant classification performance; and that the generators learn the missing views with high quality without the need of any consequent external resource.
Tasks	Machine Translation, Multiview Learning
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01861v2
PDF	https://arxiv.org/pdf/1911.01861v2.pdf
PWC	https://paperswithcode.com/paper/biconditional-generative-adversarial-networks
Repo
Framework

Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation


Title	Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
Authors	Konstantinos Pitas
Abstract	Explaining how overparametrized neural networks simultaneously achieve low risk and zero empirical risk on benchmark datasets is an open problem. PAC-Bayes bounds optimized using variational inference (VI) have been recently proposed as a promising direction in obtaining non-vacuous bounds. We show empirically that this approach gives negligible gains when modeling the posterior as a Gaussian with diagonal covariance–known as the mean-field approximation. We investigate common explanations, such as the failure of VI due to problems in optimization or choosing a suboptimal prior. Our results suggest that investigating richer posteriors is the most promising direction forward.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03009v2
PDF	https://arxiv.org/pdf/1909.03009v2.pdf
PWC	https://paperswithcode.com/paper/better-pac-bayes-bounds-for-deep-neural
Repo
Framework

Equivariant Flows: sampling configurations for multi-body systems with symmetric energies


Title	Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
Authors	Jonas Köhler, Leon Klein, Frank Noé
Abstract	Flows are exact-likelihood generative neural networks that transform samples from a simple prior distribution to the samples of the probability distribution of interest. Boltzmann Generators (BG) combine flows and statistical mechanics to sample equilibrium states of strongly interacting many-body systems such as proteins with 1000 atoms. In order to scale and generalize these results, it is essential that the natural symmetries of the probability density - in physics defined by the invariances of the energy function - are built into the flow. Here we develop theoretical tools for constructing such equivariant flows and demonstrate that a BG that is equivariant with respect to rotations and particle permutations can generalize to sampling nontrivially new configurations where a nonequivariant BG cannot.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.00753v1
PDF	https://arxiv.org/pdf/1910.00753v1.pdf
PWC	https://paperswithcode.com/paper/equivariant-flows-sampling-configurations-for
Repo
Framework

A Robust Pavement Mapping System Based on Normal-Constrained Stereo Visual Odometry


Title	A Robust Pavement Mapping System Based on Normal-Constrained Stereo Visual Odometry
Authors	Huaiyang Huang, Rui Fan, Yilong Zhu, Ming Liu, Ioannis Pitas
Abstract	Pavement condition is crucial for civil infrastructure maintenance. This task usually requires efficient road damage localization, which can be accomplished by the visual odometry system embedded in unmanned aerial vehicles (UAVs). However, the state-of-the-art visual odometry and mapping methods suffer from large drift under the degeneration of the scene structure. To alleviate this issue, we integrate normal constraints into the visual odometry process, which greatly helps to avoid large drift. By parameterizing the normal vector on the tangential plane, the normal factors are coupled with traditional reprojection factors in the pose optimization procedure. The experimental results demonstrate the effectiveness of the proposed system. The overall absolute trajectory error is improved by approximately 20%, which indicates that the estimated trajectory is much more accurate than that obtained using other state-of-the-art methods.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13102v1
PDF	https://arxiv.org/pdf/1910.13102v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-pavement-mapping-system-based-on
Repo
Framework


Title	FAIRY: A Framework for Understanding Relationships between Users’ Actions and their Social Feeds
Authors	Azin Ghazimatin, Rishiraj Saha Roy, Gerhard Weikum
Abstract	Users increasingly rely on social media feeds for consuming daily information. The items in a feed, such as news, questions, songs, etc., usually result from the complex interplay of a user’s social contacts, her interests and her actions on the platform. The relationship of the user’s own behavior and the received feed is often puzzling, and many users would like to have a clear explanation on why certain items were shown to them. Transparency and explainability are key concerns in the modern world of cognitive overload, filter bubbles, user tracking, and privacy risks. This paper presents FAIRY, a framework that systematically discovers, ranks, and explains relationships between users’ actions and items in their social media feeds. We model the user’s local neighborhood on the platform as an interaction graph, a form of heterogeneous information network constructed solely from information that is easily accessible to the concerned user. We posit that paths in this interaction graph connecting the user and her feed items can act as pertinent explanations for the user. These paths are scored with a learning-to-rank model that captures relevance and surprisal. User studies on two social platforms demonstrate the practical viability and user benefits of the FAIRY method.
Tasks	Learning-To-Rank
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03109v2
PDF	https://arxiv.org/pdf/1908.03109v2.pdf
PWC	https://paperswithcode.com/paper/fairy-a-framework-for-understanding
Repo
Framework

Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks


Title	Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks
Authors	Jaedeok Kim, Chiyoun Park, Hyun-Joo Jung, Yoonsuck Choe
Abstract	Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficult. To tackle this problem we introduce a novel concept of a trainable gate function. The trainable gate function, which confers a differentiable property to discretevalued variables, allows us to directly optimize loss functions that include non-differentiable discrete values such as 0-1 selection. The proposed trainable gate can be applied to pruning. Pruning can be carried out simply by appending the proposed trainable gate functions to each intermediate output tensor followed by fine-tuning the overall model, using any gradient-based training methods. So the proposed method can jointly optimize the selection of the pruned channels while fine-tuning the weights of the pruned model at the same time. Our experimental results demonstrate that the proposed method efficiently optimizes arbitrary neural networks in various tasks such as image classification, style transfer, optical flow estimation, and neural machine translation.
Tasks	Image Classification, Machine Translation, Optical Flow Estimation, Style Transfer
Published	2019-04-24
URL	https://arxiv.org/abs/1904.10921v2
PDF	https://arxiv.org/pdf/1904.10921v2.pdf
PWC	https://paperswithcode.com/paper/differentiable-pruning-method-for-neural
Repo
Framework

Deep learning investigation for chess player attention prediction using eye-tracking and game data


Title	Deep learning investigation for chess player attention prediction using eye-tracking and game data
Authors	Justin Le Louedec, Thomas Guntz, James Crowley, Dominique Vaufreydaz
Abstract	This article reports on an investigation of the use of convolutional neural networks to predict the visual attention of chess players. The visual attention model described in this article has been created to generate saliency maps that capture hierarchical and spatial features of chessboard, in order to predict the probability fixation for individual pixels Using a skip-layer architecture of an autoencoder, with a unified decoder, we are able to use multiscale features to predict saliency of part of the board at different scales, showing multiple relations between pieces. We have used scan path and fixation data from players engaged in solving chess problems, to compute 6600 saliency maps associated to the corresponding chess piece configurations. This corpus is completed with synthetically generated data from actual games gathered from an online chess platform. Experiments realized using both scan-paths from chess players and the CAT2000 saliency dataset of natural images, highlights several results. Deep features, pretrained on natural images, were found to be helpful in training visual attention prediction for chess. The proposed neural network architecture is able to generate meaningful saliency maps on unseen chess configurations with good scores on standard metrics. This work provides a baseline for future work on visual attention prediction in similar contexts.
Tasks	Eye Tracking
Published	2019-04-17
URL	http://arxiv.org/abs/1904.08155v1
PDF	http://arxiv.org/pdf/1904.08155v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-investigation-for-chess-player
Repo
Framework

Multi-layer Domain Adaptation for Deep Convolutional Networks


Title	Multi-layer Domain Adaptation for Deep Convolutional Networks
Authors	Ozan Ciga, Jianan Chen, Anne Martel
Abstract	Despite their success in many computer vision tasks, convolutional networks tend to require large amounts of labeled data to achieve generalization. Furthermore, the performance is not guaranteed on a sample from an unseen domain at test time, if the network was not exposed to similar samples from that domain at training time. This hinders the adoption of these techniques in clinical setting where the imaging data is scarce, and where the intra- and inter-domain variance of the data can be substantial. We propose a domain adaptation technique that is especially suitable for deep networks to alleviate this requirement of labeled data. Our method utilizes gradient reversal layers and Squeezeand-Excite modules to stabilize the training in deep networks. The proposed method was applied to publicly available histopathology and chest X-ray databases and achieved superior performance to existing state-of-the-art networks with and without domain adaptation. Depending on the application, our method can improve multi-class classification accuracy by 5-20% compared to DANN introduced in (Ganin, 2014).
Tasks	Domain Adaptation
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02620v1
PDF	https://arxiv.org/pdf/1909.02620v1.pdf
PWC	https://paperswithcode.com/paper/multi-layer-domain-adaptation-for-deep
Repo
Framework

Delivering Cognitive Behavioral Therapy Using A Conversational SocialRobot


Title	Delivering Cognitive Behavioral Therapy Using A Conversational SocialRobot
Authors	Francesca Dino, Rohola Zandie, Hojjat Abdollahi, Sarah Schoeder, Mohammad H. Mahoor
Abstract	Social robots are becoming an integrated part of our daily life due to their ability to provide companionship and entertainment. A subfield of robotics, Socially Assistive Robotics (SAR), is particularly suitable for expanding these benefits into the healthcare setting because of its unique ability to provide cognitive, social, and emotional support. This paper presents our recent research on developing SAR by evaluating the ability of a life-like conversational social robot, called Ryan, to administer internet-delivered cognitive behavioral therapy (iCBT) to older adults with depression. For Ryan to administer the therapy, we developed a dialogue-management system, called Program-R. Using an accredited CBT manual for the treatment of depression, we created seven hour-long iCBT dialogues and integrated them into Program-R using Artificial Intelligence Markup Language (AIML). To assess the effectiveness of Robot-based iCBT and users’ likability of our approach, we conducted an HRI study with a cohort of elderly people with mild-to-moderate depression over a period of four weeks. Quantitative analyses of participant’s spoken responses (e.g. word count and sentiment analysis), face-scale mood scores, and exit surveys, strongly support the notion robot-based iCBT is a viable alternative to traditional human-delivered therapy.
Tasks	Dialogue Management, Sentiment Analysis
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06670v1
PDF	https://arxiv.org/pdf/1909.06670v1.pdf
PWC	https://paperswithcode.com/paper/delivering-cognitive-behavioral-therapy-using
Repo
Framework

A tutorial on recursive models for analyzing and predicting path choice behavior


Title	A tutorial on recursive models for analyzing and predicting path choice behavior
Authors	Maëlle Zimmermann, Emma Frejinger
Abstract	The problem at the heart of this tutorial consists in modeling the path choice behavior of network users. This problem has been extensively studied in transportation science, where it is known as the route choice problem. In this literature, individuals’ choice of paths are typically predicted using discrete choice models. This article is a tutorial on a specific category of discrete choice models called recursive, and it makes three main contributions: First, for the purpose of assisting future research on route choice, we provide a comprehensive background on the problem, linking it to different fields including inverse optimization and inverse reinforcement learning. Second, we formally introduce the problem and the recursive modeling idea along with an overview of existing models, their properties and applications. Third, we extensively analyze illustrative examples from different angles so that a novice reader can gain intuition on the problem and the advantages provided by recursive models in comparison to path-based ones.
Tasks
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00883v2
PDF	https://arxiv.org/pdf/1905.00883v2.pdf
PWC	https://paperswithcode.com/paper/a-tutorial-on-recursive-models-for-analyzing
Repo
Framework

Graph Neural Network for Interpreting Task-fMRI Biomarkers


Title	Graph Neural Network for Interpreting Task-fMRI Biomarkers
Authors	Xiaoxiao Li, Nicha C. Dvornek, Yuan Zhou, Juntang Zhuang, Pamela Ventola, James S. Duncan
Abstract	Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain networks constructed by fMRI. One way to interpret important features is through looking at how the classification probability changes if the features are occluded or replaced. The major limitation of this approach is that replacing values may change the distribution of the data and lead to serious errors. Therefore, we develop a 2-stage pipeline to eliminate the need to replace features for reliable biomarker interpretation. Specifically, we propose an inductive GNN to embed the graphs containing different properties of task-fMRI for identifying ASD and then discover the brain regions/sub-graphs used as evidence for the GNN classifier. We first show GNN can achieve high accuracy in identifying ASD. Next, we calculate the feature importance scores using GNN and compare the interpretation ability with Random Forest. Finally, we run with different atlases and parameters, proving the robustness of the proposed method. The detected biomarkers reveal their association with social behaviors. We also show the potential of discovering new informative biomarkers. Our pipeline can be generalized to other graph feature importance interpretation problems.
Tasks	Feature Importance
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01661v2
PDF	https://arxiv.org/pdf/1907.01661v2.pdf
PWC	https://paperswithcode.com/paper/graph-neural-network-for-interpreting-task
Repo
Framework

Fusion Strategies for Learning User Embeddings with Neural Networks


Title	Fusion Strategies for Learning User Embeddings with Neural Networks
Authors	Philipp Blandfort, Tushar Karayil, Federico Raue, Jörn Hees, Andreas Dengel
Abstract	Growing amounts of online user data motivate the need for automated processing techniques. In case of user ratings, one interesting option is to use neural networks for learning to predict ratings given an item and a user. While training for prediction, such an approach at the same time learns to map each user to a vector, a so-called user embedding. Such embeddings can for example be valuable for estimating user similarity. However, there are various ways how item and user information can be combined in neural networks, and it is unclear how the way of combining affects the resulting embeddings. In this paper, we run an experiment on movie ratings data, where we analyze the effect on embedding quality caused by several fusion strategies in neural networks. For evaluating embedding quality, we propose a novel measure, Pair-Distance Correlation, which quantifies the condition that similar users should have similar embedding vectors. We find that the fusion strategy affects results in terms of both prediction performance and embedding quality. Surprisingly, we find that prediction performance not necessarily reflects embedding quality. This suggests that if embeddings are of interest, the common tendency to select models based on their prediction ability should be reconsidered.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02322v1
PDF	http://arxiv.org/pdf/1901.02322v1.pdf
PWC	https://paperswithcode.com/paper/fusion-strategies-for-learning-user
Repo
Framework