January 29, 2020

2950 words 14 mins read

Paper Group ANR 667

$c^+$GAN: Complementary Fashion Item Recommendation. Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques. Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors. GeoNet: Deep Geodesic Networks for Point Cloud Analysis. WEnets: A Convolutional Framework for Evaluating Audio Wave …

$c^+$GAN: Complementary Fashion Item Recommendation


Title	$c^+$GAN: Complementary Fashion Item Recommendation
Authors	Sudhir Kumar, Mithun Das Gupta
Abstract	We present a conditional generative adversarial model to draw realistic samples from paired fashion clothing distribution and provide real samples to pair with arbitrary fashion units. More concretely, given an image of a shirt, obtained from a fashion magazine, a brochure or even any random click on ones phone, we draw realistic samples from a parameterized conditional distribution learned as a conditional generative adversarial network ($c^+$GAN) to generate the possible pants which can go with the shirt. We start with a classical cGAN model as proposed by Mirza and Osindero~\cite{MirzaO14} and modify both the generator and discriminator to work on captured-in-the-wild data with no human alignment. We gather a dataset from web crawled data, systematically develop a method which counters the problems inherent to such data, and finally present plausible results based on our technique. We propose simple ideas to evaluate how these techniques can conquer the cognitive gap that exists when arbitrary clothing articles need to be paired with another relevant article, based on similarity of search results.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05596v1
PDF	https://arxiv.org/pdf/1906.05596v1.pdf
PWC	https://paperswithcode.com/paper/cgan-complementary-fashion-item
Repo
Framework

Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques


Title	Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques
Authors	Sara Mohammadinejad, Jyotirmoy V. Deshmukh, Aniruddh G. Puranic, Marcell Vazquez-Chanlatte, Alexandre Donzé
Abstract	Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these problems; however, the artifacts trained by these algorithms often lack interpretability. On the other hand, temporal logics, such as Signal Temporal Logic (STL) have been successfully used in the formal methods community as specifications of time-series behaviors. In this work, we propose a new technique to automatically learn temporal logic formulae that are able to cluster and classify real-valued time-series data. Previous work on learning STL formulas from data either assumes a formula-template to be given by the user, or assumes some special fragment of STL that enables exploring the formula structure in a systematic fashion. In our technique, we relax these assumptions, and provide a way to systematically explore the space of all STL formulas. As the space of all STL formulas is very large, and contains many semantically equivalent formulas, we suggest a technique to heuristically prune the space of formulas considered. Finally, we illustrate our technique on various case studies from the automotive, transportation and healthcare domain.
Tasks	Autonomous Vehicles, Time Series
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10265v1
PDF	https://arxiv.org/pdf/1907.10265v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-classification-of-time-series
Repo
Framework

Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors


Title	Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors
Authors	Yeping Hu, Liting Sun, Masayoshi Tomizuka
Abstract	Accurately predicting future behaviors of surrounding vehicles is an essential capability for autonomous vehicles in order to plan safe and feasible trajectories. The behaviors of others, however, are full of uncertainties. Both rational and irrational behaviors exist, and the autonomous vehicles need to be aware of this in their prediction module. The prediction module is also expected to generate reasonable results in the presence of unseen and corner scenarios. Two types of prediction models are typically used to solve the prediction problem: learning-based model and planning-based model. Learning-based model utilizes real driving data to model the human behaviors. Depending on the structure of the data, learning-based models can predict both rational and irrational behaviors. But the balance between them cannot be customized, which creates challenges in generalizing the prediction results. Planning-based model, on the other hand, usually assumes human as a rational agent, i.e., it anticipates only rational behavior of human drivers. In this paper, a generic prediction architecture is proposed to address various rationalities in human behavior. We leverage the advantages from both learning-based and planning-based prediction models. The proposed approach is able to predict continuous trajectories that well-reflect possible future situations of other drivers. Moreover, the prediction performance remains stable under various unseen driving scenarios. A case study under a real-world roundabout scenario is provided to demonstrate the performance and capability of the proposed prediction architecture.
Tasks	Autonomous Vehicles
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10170v1
PDF	https://arxiv.org/pdf/1907.10170v1.pdf
PWC	https://paperswithcode.com/paper/generic-prediction-architecture-considering
Repo
Framework

GeoNet: Deep Geodesic Networks for Point Cloud Analysis


Title	GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Authors	Tong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto
Abstract	Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds. To demonstrate the applicability of learned geodesic-aware representations, we propose fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis. Our method improves the state-of-the-art on multiple representative tasks that can benefit from understandings of the underlying surface topology, including point upsampling, normal estimation, mesh reconstruction and non-rigid shape classification.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00680v1
PDF	http://arxiv.org/pdf/1901.00680v1.pdf
PWC	https://paperswithcode.com/paper/geonet-deep-geodesic-networks-for-point-cloud
Repo
Framework

WEnets: A Convolutional Framework for Evaluating Audio Waveforms


Title	WEnets: A Convolutional Framework for Evaluating Audio Waveforms
Authors	Andrew A. Catellier, Stephen D. Voran
Abstract	We describe a new convolutional framework for waveform evaluation, WEnets, and build a Narrowband Audio Waveform Evaluation Network, or NAWEnet, using this framework. NAWEnet is single-ended (or no-reference) and was trained three separate times in order to emulate PESQ, POLQA, or STOI with testing correlations 0.95, 0.92, and 0.95, respectively when training on only 50% of available data and testing on 40%. Stacks of 1-D convolutional layers and non-linear downsampling learn which features are important for quality or intelligibility estimation. This straightforward architecture simplifies the interpretation of its inner workings and paves the way for future investigations into higher sample rates and accurate no-reference subjective speech quality predictions.
Tasks
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09024v1
PDF	https://arxiv.org/pdf/1909.09024v1.pdf
PWC	https://paperswithcode.com/paper/wenets-a-convolutional-framework-for
Repo
Framework

Topology Maintained Structure Encoding


Title	Topology Maintained Structure Encoding
Authors	Qing Fang
Abstract	Deep learning has been used as a powerful tool for various tasks in computer vision, such as image segmentation, object recognition and data generation. A key part of end-to-end training is designing the appropriate encoder to extract specific features from the input data. However, few encoders maintain the topological properties of data, such as connection structures and global contours. In this paper, we introduce a Voronoi Diagram encoder based on convex set distance (CSVD) and apply it in edge encoding. The boundaries of Voronoi cells is related to detected edges of structures and contours. The CSVD model improves contour extraction in CNN and structure generation in GAN. We also show the experimental results and demonstrate that the proposed model has great potentiality in different visual problems where topology information should be involved.
Tasks	Object Recognition, Semantic Segmentation
Published	2019-06-26
URL	https://arxiv.org/abs/1906.10823v1
PDF	https://arxiv.org/pdf/1906.10823v1.pdf
PWC	https://paperswithcode.com/paper/topology-maintained-structure-encoding
Repo
Framework

Federated AI lets a team imagine together: Federated Learning of GANs


Title	Federated AI lets a team imagine together: Federated Learning of GANs
Authors	Rajagopal. A, Nirmala. V
Abstract	Envisioning a new imaginative idea together is a popular human need. Imagining together as a team can often lead to breakthrough ideas, but the collaboration effort can also be challenging, especially when the team members are separated by time and space. What if there is a AI that can assist the team to collaboratively envision new ideas?. Is it possible to develop a working model of such an AI? This paper aims to design such an intelligence. This paper proposes a approach to design a creative and collaborative intelligence by employing a form of distributed machine learning approach called Federated Learning along with fusion on Generative Adversarial Networks, GAN. This collaborative creative AI presents a new paradigm in AI, one that lets a team of two or more to come together to imagine and envision ideas that synergies well with interests of all members of the team. In short, this paper explores the design of a novel type of AI paradigm, called Federated AI Imagination, one that lets geographically distributed teams to collaboratively imagine.
Tasks
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03595v1
PDF	https://arxiv.org/pdf/1906.03595v1.pdf
PWC	https://paperswithcode.com/paper/federated-ai-lets-a-team-imagine-together
Repo
Framework

Toward a Characterization of Loss Functions for Distribution Learning


Title	Toward a Characterization of Loss Functions for Distribution Learning
Authors	Nika Haghtalab, Cameron Musco, Bo Waggoner
Abstract	In this work we study loss functions for learning and evaluating probability distributions over large discrete domains. Unlike classification or regression where a wide variety of loss functions are used, in the distribution learning and density estimation literature, very few losses outside the dominant $log\ loss$ are applied. We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions. We start by proposing a set of desirable criteria that any good loss function should satisfy. Intuitively, these criteria require that the loss function faithfully evaluates a candidate distribution, both in expectation and when estimated on a few samples. Interestingly, we observe that \emph{no loss function} possesses all of these criteria. However, one can circumvent this issue by introducing a natural restriction on the set of candidate distributions. Specifically, we require that candidates are $calibrated$ with respect to the target distribution, i.e., they may contain less information than the target but otherwise do not significantly distort the truth. We show that, after restricting to this set of distributions, the log loss, along with a large variety of other losses satisfy the desired criteria. These results pave the way for future investigations of distribution learning that look beyond the log loss, choosing a loss function based on application or domain need.
Tasks	Density Estimation
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02652v2
PDF	https://arxiv.org/pdf/1906.02652v2.pdf
PWC	https://paperswithcode.com/paper/toward-a-characterization-of-loss-functions
Repo
Framework

Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder


Title	Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder
Authors	Xingyu Li, Marko Radulovic, Ksenija Kanjer, Konstantinos N. Plataniotis
Abstract	Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this paper, we propose a practical and self-interpretable invasive cancer diagnosis solution. With minimum annotation information, the proposed method mines contrast patterns between normal and malignant images in unsupervised manner and generates a probability map of abnormalities to verify its reasoning. Particularly, a fully convolutional autoencoder is used to learn the dominant structural patterns among normal image patches. Patches that do not share the characteristics of this normal population are detected and analyzed by one-class support vector machine and 1-layer neural network. We apply the proposed method to a public breast cancer image set. Our results, in consultation with a senior pathologist, demonstrate that the proposed method outperforms existing methods. The obtained probability map could benefit the pathology practice by providing visualized verification data and potentially leads to a better understanding of data-driven diagnosis solutions.
Tasks	Image Classification
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08670v2
PDF	http://arxiv.org/pdf/1902.08670v2.pdf
PWC	https://paperswithcode.com/paper/discriminative-pattern-mining-for-breast
Repo
Framework

Variational training of neural network approximations of solution maps for physical models


Title	Variational training of neural network approximations of solution maps for physical models
Authors	Yingzhou Li, Jianfeng Lu, Anqi Mao
Abstract	A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural network as the ansatz of the solution map and train the network variationally via loss functions from the underlying physical models. Solve-training framework avoids expensive data preparation in the traditional supervised training procedure, which prepares labels for input data, and still achieves effective representation of the solution map adapted to the input data distribution. The efficiency of solve-training framework is demonstrated through obtaining solutions maps for linear and nonlinear elliptic equations, and maps from potentials to ground states of linear and nonlinear Schr"odinger equations.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02789v2
PDF	https://arxiv.org/pdf/1905.02789v2.pdf
PWC	https://paperswithcode.com/paper/variational-training-of-neural-network
Repo
Framework

Optimal Nonparametric Inference via Deep Neural Network


Title	Optimal Nonparametric Inference via Deep Neural Network
Authors	Ruiqi Liu, Ben Boukai, Zuofeng Shang
Abstract	Deep neural network is a state-of-art method in modern science and technology. Much statistical literature have been devoted to understanding its performance in nonparametric estimation, whereas the results are suboptimal due to a redundant logarithmic sacrifice. In this paper, we show that such log-factors are not necessary. We derive upper bounds for the $L^2$ minimax risk in nonparametric estimation. Sufficient conditions on network architectures are provided such that the upper bounds become optimal (without log-sacrifice). Our proof relies on an explicitly constructed network estimator based on tensor product B-splines. We also derive asymptotic distributions for the constructed network and a relating hypothesis testing procedure. The testing procedure is further proven as minimax optimal under suitable network architectures.
Tasks
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01687v1
PDF	http://arxiv.org/pdf/1902.01687v1.pdf
PWC	https://paperswithcode.com/paper/optimal-nonparametric-inference-via-deep
Repo
Framework

Prediction of Small Molecule Kinase Inhibitors for Chemotherapy Using Deep Learning


Title	Prediction of Small Molecule Kinase Inhibitors for Chemotherapy Using Deep Learning
Authors	Niranjan Balachandar, Christine Liu, Winston Wang
Abstract	The current state of cancer therapeutics has been moving away from one-size-fits-all cytotoxic chemotherapy, and towards a more individualized and specific approach involving the targeting of each tumor’s genetic vulnerabilities. Different tumors, even of the same type, may be more reliant on certain cellular pathways more than others. With modern advancements in our understanding of cancer genome sequencing, these pathways can be discovered. Investigating each of the millions of possible small molecule inhibitors for each kinase in vitro, however, would be extremely expensive and time consuming. This project focuses on predicting the inhibition activity of small molecules targeting 8 different kinases using multiple deep learning models. We trained fingerprint-based MLPs and simplified molecular-input line-entry specification (SMILES)-based recurrent neural networks (RNNs) and molecular graph convolutional networks (GCNs) to accurately predict inhibitory activity targeting these 8 kinases.
Tasks
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00329v1
PDF	https://arxiv.org/pdf/1907.00329v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-small-molecule-kinase
Repo
Framework

Higher-Order Function Networks for Learning Composable 3D Object Representations


Title	Higher-Order Function Networks for Learning Composable 3D Object Representations
Authors	Eric Mitchell, Selim Engin, Volkan Isler, Daniel D Lee
Abstract	We present a method to represent 3D objects using higher order functions, where an object is encoded directly into the weights and biases of a small mapping' network by a larger encoder network. This mapping network can be used to reconstruct 3D objects by applying its encoded transformation to points sampled from a simple canonical space. We first demonstrate that an encoder network can produce mappings that reconstruct objects from single images more accurately than state of the art point set reconstruction methods. Next, we show that our method yields meaningful gains for robot motion planning problems that use this object representation for collision avoidance. We also demonstrate that our formulation allows for a novel method of object interpolation in a latent function space, where we compose the roots of the reconstruction functions for various objects to generate new, coherent objects. Finally, we demonstrate the coding efficiency of our approach: encoding objects directly as a neural network is highly parameter efficient when compared with object representations that encode the object of interest as a latent vector codeword’. Our smallest reconstruction network has only about 7000 parameters and shows reconstruction quality generally better than state-of-the-art codeword-based object representation architectures with millions of parameters.
Tasks	Motion Planning
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10388v1
PDF	https://arxiv.org/pdf/1907.10388v1.pdf
PWC	https://paperswithcode.com/paper/higher-order-function-networks-for-learning
Repo
Framework

Bias In, Bias Out? Evaluating the Folk Wisdom


Title	Bias In, Bias Out? Evaluating the Folk Wisdom
Authors	Ashesh Rambachan, Jonathan Roth
Abstract	We evaluate the folk wisdom that algorithmic decision rules trained on data produced by biased human decision-makers necessarily reflect this bias. We consider a setting where training labels are only generated if a biased decision-maker takes a particular action, and so “biased” training data arise due to discriminatory selection into the training data. In our baseline model, the more biased the decision-maker is against a group, the more the algorithmic decision rule favors that group. We refer to this phenomenon as “bias reversal.” We then clarify the conditions that give rise to bias reversal. Whether a prediction algorithm reverses or inherits bias depends critically on how the decision-maker affects the training data as well as the label used in training. We illustrate our main theoretical results in a simulation study applied to the New York City Stop, Question and Frisk dataset.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08518v2
PDF	https://arxiv.org/pdf/1909.08518v2.pdf
PWC	https://paperswithcode.com/paper/bias-in-bias-out-evaluating-the-folk-wisdom
Repo
Framework

Sequential Controlled Sensing for Composite Multihypothesis Testing


Title	Sequential Controlled Sensing for Composite Multihypothesis Testing
Authors	Aditya Deshmukh, Srikrishna Bhashyam, Venugopal V. Veeravalli
Abstract	The problem of multi-hypothesis testing with controlled sensing of observations is considered. The distribution of observations collected under each control is assumed to follow a single-parameter exponential family distribution. The goal is to design a policy to find the true hypothesis with minimum expected delay while ensuring that the probability of error is below a given constraint. The decision-maker can control the delay by intelligently choosing the control for observation collection in each time slot. We derive a policy that satisfies the given constraint on the error probability. We also show that the policy is asymptotically optimal in the sense that it asymptotically achieves an information-theoretic lower bound on the expected delay.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.12697v1
PDF	https://arxiv.org/pdf/1910.12697v1.pdf
PWC	https://paperswithcode.com/paper/sequential-controlled-sensing-for-composite
Repo
Framework