October 18, 2019

2845 words 14 mins read

Paper Group ANR 467

Drug cell line interaction prediction. Full 3D Reconstruction of Transparent Objects. Normal Similarity Network for Generative Modelling. Capsule Networks for Protein Structure Classification and Prediction. Hybrid Model For Word Prediction Using Naive Bayes and Latent Information. K for the Price of 1: Parameter-efficient Multi-task and Transfer L …

Drug cell line interaction prediction


Title	Drug cell line interaction prediction
Authors	Pengfei Liu
Abstract	Understanding the phenotypic drug response on cancer cell lines plays a vital rule in anti-cancer drug discovery and re-purposing. The Genomics of Drug Sensitivity in Cancer (GDSC) database provides open data for researchers in phenotypic screening to test their models and methods. Previously, most research in these areas starts from the fingerprints or features of drugs, instead of their structures. In this paper, we introduce a model for phenotypic screening, which is called twin Convolutional Neural Network for drugs in SMILES format (tCNNS). tCNNS is comprised of CNN input channels for drugs in SMILES format and cancer cell lines respectively. Our model achieves $0.84$ for the coefficient of determinant($R^2$) and $0.92$ for Pearson correlation($R_p$), which are significantly better than previous works\cite{ammad2014integrative,haider2015copula,menden2013machine}. Besides these statistical metrics, tCNNS also provides some insights into phenotypic screening.
Tasks	Drug Discovery
Published	2018-12-28
URL	http://arxiv.org/abs/1812.11178v1
PDF	http://arxiv.org/pdf/1812.11178v1.pdf
PWC	https://paperswithcode.com/paper/drug-cell-line-interaction-prediction
Repo
Framework

Full 3D Reconstruction of Transparent Objects


Title	Full 3D Reconstruction of Transparent Objects
Authors	Bojian Wu, Yang Zhou, Yiming Qian, Minglun Gong, Hui Huang
Abstract	Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing complete 3D shapes of transparent objects. Through positioning an object on a turntable, its silhouettes and light refraction paths under different viewing directions are captured. Then, starting from an initial rough model generated from space carving, our algorithm progressively optimizes the model under three constraints: surface and refraction normal consistency, surface projection and silhouette consistency, and surface smoothness. Experimental results on both synthetic and real objects demonstrate that our method can successfully recover the complex shapes of transparent objects and faithfully reproduce their light refraction properties.
Tasks	3D Reconstruction
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03482v2
PDF	http://arxiv.org/pdf/1805.03482v2.pdf
PWC	https://paperswithcode.com/paper/full-3d-reconstruction-of-transparent-objects
Repo
Framework

Normal Similarity Network for Generative Modelling


Title	Normal Similarity Network for Generative Modelling
Authors	Jay Nandy, Wynne Hsu, Mong Li Lee
Abstract	Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal Similarity Network (NSN) where the layers are constructed with Gaussian-style filters. NSN is trained with a layer-wise non-parametric density estimation algorithm that iteratively down-samples the training images and captures the density of the down-sampled training images in the final layer. Additionally, we propose NSN-Gen for generating new samples from noise vectors by iteratively reconstructing feature maps in the hidden layers of NSN. Our experiments suggest encouraging results of the proposed model for a wide range of computer vision applications including image generation, styling and reconstruction from occluded images.
Tasks	Density Estimation, Image Generation
Published	2018-05-14
URL	http://arxiv.org/abs/1805.05269v1
PDF	http://arxiv.org/pdf/1805.05269v1.pdf
PWC	https://paperswithcode.com/paper/normal-similarity-network-for-generative
Repo
Framework

Capsule Networks for Protein Structure Classification and Prediction


Title	Capsule Networks for Protein Structure Classification and Prediction
Authors	Dan Rosa de Jesus, Julian Cuevas, Wilson Rivera, Silvia Crivelli
Abstract	Capsule Networks have great potential to tackle problems in structural biology because of their attention to hierarchical relationships. This paper describes the implementation and application of a Capsule Network architecture to the classification of RAS protein family structures on GPU-based computational resources. The proposed Capsule Network trained on 2D and 3D structural encodings can successfully classify HRAS and KRAS structures. The Capsule Network can also classify a protein-based dataset derived from a PSI-BLAST search on sequences of KRAS and HRAS mutations. Our results show an accuracy improvement compared to traditional convolutional networks, while improving interpretability through visualization of activation vectors.
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07475v1
PDF	http://arxiv.org/pdf/1808.07475v1.pdf
PWC	https://paperswithcode.com/paper/capsule-networks-for-protein-structure
Repo
Framework

Hybrid Model For Word Prediction Using Naive Bayes and Latent Information


Title	Hybrid Model For Word Prediction Using Naive Bayes and Latent Information
Authors	Henrique X. Goulart, Mauro D. L. Tosi, Daniel Soares Gonçalves, Rodrigo F. Maia, Guilherme A. Wachs-Lopes
Abstract	Historically, the Natural Language Processing area has been given too much attention by many researchers. One of the main motivation beyond this interest is related to the word prediction problem, which states that given a set words in a sentence, one can recommend the next word. In literature, this problem is solved by methods based on syntactic or semantic analysis. Solely, each of these analysis cannot achieve practical results for end-user applications. For instance, the Latent Semantic Analysis can handle semantic features of text, but cannot suggest words considering syntactical rules. On the other hand, there are models that treat both methods together and achieve state-of-the-art results, e.g. Deep Learning. These models can demand high computational effort, which can make the model infeasible for certain types of applications. With the advance of the technology and mathematical models, it is possible to develop faster systems with more accuracy. This work proposes a hybrid word suggestion model, based on Naive Bayes and Latent Semantic Analysis, considering neighbouring words around unfilled gaps. Results show that this model could achieve 44.2% of accuracy in the MSR Sentence Completion Challenge.
Tasks
Published	2018-03-02
URL	http://arxiv.org/abs/1803.00985v1
PDF	http://arxiv.org/pdf/1803.00985v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-model-for-word-prediction-using-naive
Repo
Framework

K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning


Title	K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
Authors	Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew Howard
Abstract	We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that learning a set of scales and biases is sufficient to convert a pretrained network to perform well on qualitatively different problems (e.g. converting a Single Shot MultiBox Detection (SSD) model into a 1000-class image classification model while reusing 98% of parameters of the SSD feature extractor). Similarly, we show that re-learning existing low-parameter layers (such as depth-wise convolutions) while keeping the rest of the network frozen also improves transfer-learning accuracy significantly. Our approach allows both simultaneous (multi-task) as well as sequential transfer learning. In several multi-task learning problems, despite using much fewer parameters than traditional logits-only fine-tuning, we match single-task performance.
Tasks	Image Classification, Multi-Task Learning, Transfer Learning
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10703v2
PDF	http://arxiv.org/pdf/1810.10703v2.pdf
PWC	https://paperswithcode.com/paper/k-for-the-price-of-1-parameter-efficient
Repo
Framework

Simultaneous Parameter Learning and Bi-Clustering for Multi-Response Models


Title	Simultaneous Parameter Learning and Bi-Clustering for Multi-Response Models
Authors	Ming Yu, Karthikeyan Natesan Ramamurthy, Addie Thompson, Aurélie Lozano
Abstract	We consider multi-response and multitask regression models, where the parameter matrix to be estimated is expected to have an unknown grouping structure. The groupings can be along tasks, or features, or both, the last one indicating a bi-cluster or “checkerboard” structure. Discovering this grouping structure along with parameter inference makes sense in several applications, such as multi-response Genome-Wide Association Studies. This additional structure can not only can be leveraged for more accurate parameter estimation, but it also provides valuable information on the underlying data mechanisms (e.g. relationships among genotypes and phenotypes in GWAS). In this paper, we propose two formulations to simultaneously learn the parameter matrix and its group structures, based on convex regularization penalties. We present optimization approaches to solve the resulting problems and provide numerical convergence guarantees. Our approaches are validated on extensive simulations and real datasets concerning phenotypes and genotypes of plant varieties.
Tasks
Published	2018-04-29
URL	http://arxiv.org/abs/1804.10961v1
PDF	http://arxiv.org/pdf/1804.10961v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-parameter-learning-and-bi
Repo
Framework

Convex Relaxation Methods for Community Detection


Title	Convex Relaxation Methods for Community Detection
Authors	Xiaodong Li, Yudong Chen, Jiaming Xu
Abstract	This paper surveys recent theoretical advances in convex optimization approaches for community detection. We introduce some important theoretical techniques and results for establishing the consistency of convex community detection under various statistical models. In particular, we discuss the basic techniques based on the primal and dual analysis. We also present results that demonstrate several distinctive advantages of convex community detection, including robustness against outlier nodes, consistency under weak assortativity, and adaptivity to heterogeneous degrees. This survey is not intended to be a complete overview of the vast literature on this fast-growing topic. Instead, we aim to provide a big picture of the remarkable recent development in this area and to make the survey accessible to a broad audience. We hope that this expository article can serve as an introductory guide for readers who are interested in using, designing, and analyzing convex relaxation methods in network analysis.
Tasks	Community Detection
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00315v1
PDF	http://arxiv.org/pdf/1810.00315v1.pdf
PWC	https://paperswithcode.com/paper/convex-relaxation-methods-for-community
Repo
Framework

Uplift Modeling from Separate Labels


Title	Uplift Modeling from Separate Labels
Authors	Ikko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama
Abstract	Uplift modeling is aimed at estimating the incremental impact of an action on an individual’s behavior, which is useful in various application domains such as targeted marketing (advertisement campaigns) and personalized medicine (medical treatments). Conventional methods of uplift modeling require every instance to be jointly equipped with two types of labels: the taken action and its outcome. However, obtaining two labels for each instance at the same time is difficult or expensive in many real-world problems. In this paper, we propose a novel method of uplift modeling that is applicable to a more practical setting where only one type of labels is available for each instance. We show a mean squared error bound for the proposed estimator and demonstrate its effectiveness through experiments.
Tasks
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05112v5
PDF	http://arxiv.org/pdf/1803.05112v5.pdf
PWC	https://paperswithcode.com/paper/uplift-modeling-from-separate-labels
Repo
Framework

Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning


Title	Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Authors	Wei Zhu, Qiang Qiu, Bao Wang, Jianfeng Lu, Guillermo Sapiro, Ingrid Daubechies
Abstract	Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed. We find out that the reason for this is the inconsistency between the enforced geometry and the standard softmax cross entropy loss. To resolve this, we propose a new framework for data-dependent DNN regularization, the Geometrically-Regularized-Self-Validating neural Networks (GRSVNet). During training, the geometry enforced on one batch of features is simultaneously validated on a separate batch using a validation loss consistent with the geometry. We study a particular case of GRSVNet, the Orthogonal-Low-rank Embedding (OLE)-GRSVNet, which is capable of producing highly discriminative features residing in orthogonal low-rank subspaces. Numerical experiments show that OLE-GRSVNet outperforms DNNs with conventional regularization when trained on real data. More importantly, unlike conventional DNNs, OLE-GRSVNet refuses to memorize random data or random labels, suggesting it only learns intrinsic patterns by reducing the memorizing capacity of the baseline DNN.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07291v2
PDF	http://arxiv.org/pdf/1805.07291v2.pdf
PWC	https://paperswithcode.com/paper/stop-memorizing-a-data-dependent
Repo
Framework

Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System


Title	Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System
Authors	Barbara Rychalska, Dominika Basaj, Przemyslaw Biecek, Anna Wroblewska
Abstract	In this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset. We show that main verbs in questions carry little influence on the decisions made by the system - in over 90% of researched cases swapping verbs for their antonyms did not change system decision. We track this phenomenon down to the insides of the net, analyzing the mechanism of self-attention and values contained in hidden layers of RNN. Finally, we recognize the characteristics of the SQuAD dataset as the source of the problem. Our work refers to the recently popular topic of adversarial examples in NLP, combined with investigating deep net structure.
Tasks
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03740v1
PDF	http://arxiv.org/pdf/1809.03740v1.pdf
PWC	https://paperswithcode.com/paper/does-it-care-what-you-asked-understanding
Repo
Framework

CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation


Title	CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation
Authors	Dakai Jin, Ziyue Xu, Youbao Tang, Adam P. Harrison, Daniel J. Mollura
Abstract	Data availability plays a critical role for the performance of deep learning systems. This challenge is especially acute within the medical image domain, particularly when pathologies are involved, due to two factors: 1) limited number of cases, and 2) large variations in location, scale, and appearance. In this work, we investigate whether augmenting a dataset with artificially generated lung nodules can improve the robustness of the progressive holistically nested network (P-HNN) model for pathological lung segmentation of CT scans. To achieve this goal, we develop a 3D generative adversarial network (GAN) that effectively learns lung nodule property distributions in 3D space. In order to embed the nodules within their background context, we condition the GAN based on a volume of interest whose central part containing the nodule has been erased. To further improve realism and blending with the background, we propose a novel multi-mask reconstruction loss. We train our method on over 1000 nodules from the LIDC dataset. Qualitative results demonstrate the effectiveness of our method compared to the state-of-art. We then use our GAN to generate simulated training images where nodules lie on the lung border, which are cases where the published P-HNN model struggles. Qualitative and quantitative results demonstrate that armed with these simulated images, the P-HNN model learns to better segment lung regions under these challenging situations. As a result, our system provides a promising means to help overcome the data paucity that commonly afflicts medical imaging.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.04051v1
PDF	http://arxiv.org/pdf/1806.04051v1.pdf
PWC	https://paperswithcode.com/paper/ct-realistic-lung-nodule-simulation-from-3d
Repo
Framework

Welfare and Distributional Impacts of Fair Classification


Title	Welfare and Distributional Impacts of Fair Classification
Authors	Lily Hu, Yiling Chen
Abstract	Current methodologies in machine learning analyze the effects of various statistical parity notions of fairness primarily in light of their impacts on predictive accuracy and vendor utility loss. In this paper, we propose a new framework for interpreting the effects of fairness criteria by converting the constrained loss minimization problem into a social welfare maximization problem. This translation moves a classifier and its output into utility space where individuals, groups, and society at-large experience different welfare changes due to classification assignments. Under this characterization, predictions and fairness constraints are seen as shaping societal welfare and distribution and revealing individuals’ implied welfare weights in society–weights that may then be interpreted through a fairness lens. The social welfare formulation of the fairness problem brings to the fore concerns of distributive justice that have always had a central albeit more implicit role in standard algorithmic fairness approaches.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01134v1
PDF	http://arxiv.org/pdf/1807.01134v1.pdf
PWC	https://paperswithcode.com/paper/welfare-and-distributional-impacts-of-fair
Repo
Framework

Cognitive Action Laws: The Case of Visual Features


Title	Cognitive Action Laws: The Case of Visual Features
Authors	Alessandro Betti, Marco Gori, Stefano Melacci
Abstract	This paper proposes a theory for understanding perceptual learning processes within the general framework of laws of nature. Neural networks are regarded as systems whose connections are Lagrangian variables, namely functions depending on time. They are used to minimize the cognitive action, an appropriate functional index that measures the agent interactions with the environment. The cognitive action contains a potential and a kinetic term that nicely resemble the classic formulation of regularization in machine learning. A special choice of the functional index, which leads to forth-order differential equations—Cognitive Action Laws (CAL)—exhibits a structure that mirrors classic formulation of machine learning. In particular, unlike the action of mechanics, the stationarity condition corresponds with the global minimum. Moreover, it is proven that typical asymptotic learning conditions on the weights can coexist with the initialization provided that the system dynamics is driven under a policy referred to as information overloading control. Finally, the theory is experimented for the problem of feature extraction in computer vision.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09162v1
PDF	http://arxiv.org/pdf/1808.09162v1.pdf
PWC	https://paperswithcode.com/paper/cognitive-action-laws-the-case-of-visual
Repo
Framework

Pairwise Augmented GANs with Adversarial Reconstruction Loss


Title	Pairwise Augmented GANs with Adversarial Reconstruction Loss
Authors	Aibek Alanov, Max Kochurov, Daniil Yashkov, Dmitry Vetrov
Abstract	We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the same time is trained to map the true data distribution to the prior in latent space. To ensure good reconstructions, we introduce an augmented adversarial reconstruction loss. Here we train a discriminator to distinguish two types of pairs: an object with its augmentation and the one with its reconstruction. We show that such adversarial loss compares objects based on the content rather than on the exact match. We experimentally demonstrate that our model generates samples and reconstructions of quality competitive with state-of-the-art on datasets MNIST, CIFAR10, CelebA and achieves good quantitative results on CIFAR10.
Tasks
Published	2018-10-11
URL	http://arxiv.org/abs/1810.04920v1
PDF	http://arxiv.org/pdf/1810.04920v1.pdf
PWC	https://paperswithcode.com/paper/pairwise-augmented-gans-with-adversarial
Repo
Framework