October 20, 2019

3396 words 16 mins read

Paper Group AWR 225

Clustering with Deep Learning: Taxonomy and New Methods. Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification. DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection. Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews. SQL-Rank: A Listw …

Clustering with Deep Learning: Taxonomy and New Methods


Title	Clustering with Deep Learning: Taxonomy and New Methods
Authors	Elie Aljalbout, Vladimir Golkov, Yawar Siddiqui, Maximilian Strobel, Daniel Cremers
Abstract	Clustering methods based on deep neural networks have proven promising for clustering real-world data because of their high representational power. In this paper, we propose a systematic taxonomy of clustering methods that utilize deep neural networks. We base our taxonomy on a comprehensive review of recent work and validate the taxonomy in a case study. In this case study, we show that the taxonomy enables researchers and practitioners to systematically create new clustering methods by selectively recombining and replacing distinct aspects of previous methods with the goal of overcoming their individual limitations. The experimental evaluation confirms this and shows that the method created for the case study achieves state-of-the-art clustering quality and surpasses it in some cases.
Tasks
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07648v2
PDF	http://arxiv.org/pdf/1801.07648v2.pdf
PWC	https://paperswithcode.com/paper/clustering-with-deep-learning-taxonomy-and
Repo	https://github.com/elieJalbout/Clustering-with-Deep-learning
Framework	none

Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification


Title	Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
Authors	Zheng Li, Ying Wei, Yu Zhang, Xiang Zhang, Xin Li, Qiang Yang
Abstract	Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are all relatively small. Meanwhile, most of the previous methods rely on complicated structures with given scarce data, which largely limits the efficacy of the neural models. In this paper, we exploit a new direction named coarse-to-fine task transfer, which aims to leverage knowledge learned from a rich-resource source domain of the coarse-grained AC task, which is more easily accessible, to improve the learning in a low-resource target domain of the fine-grained AT task. To resolve both the aspect granularity inconsistency and feature mismatch between domains, we propose a Multi-Granularity Alignment Network (MGAN). In MGAN, a novel Coarse2Fine attention guided by an auxiliary task can help the AC task modeling at the same fine-grained level with the AT task. To alleviate the feature false alignment, a contrastive feature alignment method is adopted to align aspect-specific feature representations semantically. In addition, a large-scale multi-domain dataset for the AC task is provided. Empirically, extensive experiments demonstrate the effectiveness of the MGAN.
Tasks	Sentiment Analysis
Published	2018-11-16
URL	http://arxiv.org/abs/1811.10999v1
PDF	http://arxiv.org/pdf/1811.10999v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-coarse-to-fine-task-transfer-for
Repo	https://github.com/hsqmlzno1/MGAN
Framework	none

DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection


Title	DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection
Authors	Renqiang Li, Hong Liu, Xiangdong Wan, Yueliang Qian
Abstract	Braille is an effective way for the visually impaired to learn knowledge and obtain information. Braille image recognition aims to automatically detect Braille dots in the whole Braille image. There is no available public datasets for Braille image recognition to push relevant research and evaluate algorithms. This paper constructs a large-scale Double-Sided Braille Image dataset DSBI with detailed Braille recto dots, verso dots and Braille cells annotation. To quickly annotate Braille images, an auxiliary annotation strategy is proposed, which adopts initial automatic detection of Braille dots and modifies annotation results by convenient human-computer interaction method. This labeling strategy can averagely increase label efficiency by six times for recto dots annotation in one Braille image. Braille dots detection is the core and basic step for Braille image recognition. This paper also evaluates some Braille dots detection methods on our dataset DSBI and gives the benchmark performance of recto dots detection. We have released our Braille images dataset on the GitHub website.
Tasks
Published	2018-11-27
URL	http://arxiv.org/abs/1811.10893v2
PDF	http://arxiv.org/pdf/1811.10893v2.pdf
PWC	https://paperswithcode.com/paper/dsbi-double-sided-braille-image-dataset-and
Repo	https://github.com/yeluo1994/DSBI
Framework	none

Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews


Title	Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews
Authors	Zheng Chen, Yong Zhang, Yue Shang, Xiaohua Hu
Abstract	This paper proposes a new HDP based online review rating regression model named Topic-Sentiment-Preference Regression Analysis (TSPRA). TSPRA combines topics (i.e. product aspects), word sentiment and user preference as regression factors, and is able to perform topic clustering, review rating prediction, sentiment analysis and what we invent as “critical aspect” analysis altogether in one framework. TSPRA extends sentiment approaches by integrating the key concept “user preference” in collaborative filtering (CF) models into consideration, while it is distinct from current CF models by decoupling “user preference” and “sentiment” as independent factors. Our experiments conducted on 22 Amazon datasets show overwhelming better performance in rating predication against a state-of-art model FLAME (2015) in terms of error, Pearson’s Correlation and number of inverted pairs. For sentiment analysis, we compare the derived word sentiments against a public sentiment resource SenticNet3 and our sentiment estimations clearly make more sense in the context of online reviews. Last, as a result of the de-correlation of “user preference” from “sentiment”, TSPRA is able to evaluate a new concept “critical aspects”, defined as the product aspects seriously concerned by users but negatively commented in reviews. Improvement to such “critical aspects” could be most effective to enhance user experience.
Tasks	Online Review Rating, Sentiment Analysis
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07805v1
PDF	http://arxiv.org/pdf/1812.07805v1.pdf
PWC	https://paperswithcode.com/paper/unifying-topic-sentiment-preference-in-an-hdp
Repo	https://github.com/tonyrivermsfly/TSPRA
Framework	none

SQL-Rank: A Listwise Approach to Collaborative Ranking


Title	SQL-Rank: A Listwise Approach to Collaborative Ranking
Authors	Liwei Wu, Cho-Jui Hsieh, James Sharpnack
Abstract	In this paper, we propose a listwise approach for constructing user-specific rankings in recommendation systems in a collaborative fashion. We contrast the listwise approach to previous pointwise and pairwise approaches, which are based on treating either each rating or each pairwise comparison as an independent instance respectively. By extending the work of (Cao et al. 2007), we cast listwise collaborative ranking as maximum likelihood under a permutation model which applies probability mass to permutations based on a low rank latent score matrix. We present a novel algorithm called SQL-Rank, which can accommodate ties and missing data and can run in linear time. We develop a theoretical framework for analyzing listwise ranking methods based on a novel representation theory for the permutation model. Applying this framework to collaborative ranking, we derive asymptotic statistical rates as the number of users and items grow together. We conclude by demonstrating that our SQL-Rank method often outperforms current state-of-the-art algorithms for implicit feedback such as Weighted-MF and BPR and achieve favorable results when compared to explicit feedback algorithms such as matrix factorization and collaborative ranking.
Tasks	Collaborative Ranking, Recommendation Systems
Published	2018-02-28
URL	http://arxiv.org/abs/1803.00114v3
PDF	http://arxiv.org/pdf/1803.00114v3.pdf
PWC	https://paperswithcode.com/paper/sql-rank-a-listwise-approach-to-collaborative
Repo	https://github.com/wuliwei9278/SQL-Rank
Framework	none


Title	Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning
Authors	Changan Chen, Yuejiang Liu, Sven Kreiss, Alexandre Alahi
Abstract	Mobility in an effective and socially-compliant manner is an essential yet challenging task for robots operating in crowded spaces. Recent works have shown the power of deep reinforcement learning techniques to learn socially cooperative policies. However, their cooperation ability deteriorates as the crowd grows since they typically relax the problem as a one-way Human-Robot interaction problem. In this work, we want to go beyond first-order Human-Robot interaction and more explicitly model Crowd-Robot Interaction (CRI). We propose to (i) rethink pairwise interactions with a self-attention mechanism, and (ii) jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework. Our model captures the Human-Human interactions occurring in dense crowds that indirectly affects the robot’s anticipation capability. Our proposed attentive pooling mechanism learns the collective importance of neighboring humans with respect to their future states. Various experiments demonstrate that our model can anticipate human dynamics and navigate in crowds with time efficiency, outperforming state-of-the-art methods.
Tasks	Human Dynamics, Robot Navigation
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08835v2
PDF	http://arxiv.org/pdf/1809.08835v2.pdf
PWC	https://paperswithcode.com/paper/crowd-robot-interaction-crowd-aware-robot
Repo	https://github.com/vita-epfl/DyNav
Framework	none

KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images


Title	KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images
Authors	Isidro Cortes Ciriano, Andreas Bender
Abstract	The application of convolutional neural networks (ConvNets) to harness high-content screening images or 2D compound representations is gaining increasing attention in drug discovery. However, existing applications often require large data sets for training, or sophisticated pretraining schemes. Here, we show using 33 IC50 data sets from ChEMBL 23 that the in vitro activity of compounds on cancer cell lines and protein targets can be accurately predicted on a continuous scale from their Kekule structure representations alone by extending existing architectures, which were pretrained on unrelated image data sets. We show that the predictive power of the generated models is comparable to that of Random Forest (RF) models and fully-connected Deep Neural Networks trained on circular (Morgan) fingerprints. Notably, including additional fully-connected layers further increases the predictive power of the ConvNets by up to 10%. Analysis of the predictions generated by RF models and ConvNets shows that by simply averaging the output of the RF models and ConvNets we obtain significantly lower errors in prediction for multiple data sets, although the effect size is small, than those obtained with either model alone, indicating that the features extracted by the convolutional layers of the ConvNets provide complementary predictive signal to Morgan fingerprints. Lastly, we show that multi-task ConvNets trained on compound images permit to model COX isoform selectivity on a continuous scale with errors in prediction comparable to the uncertainty of the data. Overall, in this work we present a set of ConvNet architectures for the prediction of compound activity from their Kekule structure representations with state-of-the-art performance, that require no generation of compound descriptors or use of sophisticated image processing techniques.
Tasks	Drug Discovery, Prediction Of Cancer Cell Line Sensitivity
Published	2018-11-22
URL	https://arxiv.org/abs/1811.09036v2
PDF	https://arxiv.org/pdf/1811.09036v2.pdf
PWC	https://paperswithcode.com/paper/kekulescope-improved-prediction-of-cancer
Repo	https://github.com/isidroc/kekulescope
Framework	pytorch

Character-Level Models versus Morphology in Semantic Role Labeling


Title	Character-Level Models versus Morphology in Semantic Role Labeling
Authors	Gözde Gül Şahin, Mark Steedman
Abstract	Character-level models have become a popular approach specially for their accessibility and ability to handle unseen data. However, little is known on their ability to reveal the underlying morphological structure of a word, which is a crucial skill for high-level semantic analysis tasks, such as semantic role labeling (SRL). In this work, we train various types of SRL models that use word, character and morphology level information and analyze how performance of characters compare to words and morphology for several languages. We conduct an in-depth error analysis for each morphological typology and analyze the strengths and limitations of character-level models that relate to out-of-domain data, training data size, long range dependencies and model complexity. Our exhaustive analyses shed light on important characteristics of character-level models and their semantic capability.
Tasks	Semantic Role Labeling
Published	2018-05-30
URL	http://arxiv.org/abs/1805.11937v1
PDF	http://arxiv.org/pdf/1805.11937v1.pdf
PWC	https://paperswithcode.com/paper/character-level-models-versus-morphology-in
Repo	https://github.com/gozdesahin/Subword_Semantic_Role_Labeling
Framework	pytorch

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations


Title	Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Authors	Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
Abstract	The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challenge some common assumptions. We first theoretically show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data. Then, we train more than 12000 models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets. We observe that while the different methods successfully enforce properties ``encouraged’’ by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Furthermore, increased disentanglement does not seem to lead to a decreased sample complexity of learning for downstream tasks. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets. \|
Tasks	Representation Learning
Published	2018-11-29
URL	https://arxiv.org/abs/1811.12359v4
PDF	https://arxiv.org/pdf/1811.12359v4.pdf
PWC	https://paperswithcode.com/paper/challenging-common-assumptions-in-the
Repo	https://github.com/WGierke/CSBestPaperAwards
Framework	none

Convex Hull Approximation of Nearly Optimal Lasso Solutions


Title	Convex Hull Approximation of Nearly Optimal Lasso Solutions
Authors	Satoshi Hara, Takanori Maehara
Abstract	In an ordinary feature selection procedure, a set of important features is obtained by solving an optimization problem such as the Lasso regression problem, and we expect that the obtained features explain the data well. In this study, instead of the single optimal solution, we consider finding a set of diverse yet nearly optimal solutions. To this end, we formulate the problem as finding a small number of solutions such that the convex hull of these solutions approximates the set of nearly optimal solutions. The proposed algorithm consists of two steps: First, we randomly sample the extreme points of the set of nearly optimal solutions. Then, we select a small number of points using a greedy algorithm. The experimental results indicate that the proposed algorithm can approximate the solution set well. The results also indicate that we can obtain Lasso solutions with a large diversity.
Tasks	Feature Selection
Published	2018-10-14
URL	http://arxiv.org/abs/1810.05992v1
PDF	http://arxiv.org/pdf/1810.05992v1.pdf
PWC	https://paperswithcode.com/paper/convex-hull-approximation-of-nearly-optimal
Repo	https://github.com/sato9hara/LassoHull
Framework	none

Iterative Residual CNNs for Burst Photography Applications


Title	Iterative Residual CNNs for Burst Photography Applications
Authors	Filippos Kokkinos, Stamatios Lefkimmiatis
Abstract	Modern inexpensive imaging sensors suffer from inherent hardware constraints which often result in captured images of poor quality. Among the most common ways to deal with such limitations is to rely on burst photography, which nowadays acts as the backbone of all modern smartphone imaging applications. In this work, we focus on the fact that every frame of a burst sequence can be accurately described by a forward (physical) model. This in turn allows us to restore a single image of higher quality from a sequence of low quality images as the solution of an optimization problem. Inspired by an extension of the gradient descent method that can handle non-smooth functions, namely the proximal gradient descent, and modern deep learning techniques, we propose a convolutional iterative network with a transparent architecture. Our network, uses a burst of low quality image frames and is able to produce an output of higher image quality recovering fine details which are not distinguishable in any of the original burst frames. We focus both on the burst photography pipeline as a whole, i.e. burst demosaicking and denoising, as well as on the traditional Gaussian denoising task. The developed method demonstrates consistent state-of-the art performance across the two tasks and as opposed to other recent deep learning approaches does not have any inherent restrictions either to the number of frames or their ordering. Code can be found at https://fkokkinos.github.io/deep_burst/
Tasks	Demosaicking, Denoising, Image Restoration
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12197v2
PDF	http://arxiv.org/pdf/1811.12197v2.pdf
PWC	https://paperswithcode.com/paper/iterative-residual-cnns-for-burst-photography
Repo	https://github.com/cig-skoltech/burst-cvpr-2019
Framework	pytorch

Adjusting for Confounding in Unsupervised Latent Representations of Images


Title	Adjusting for Confounding in Unsupervised Latent Representations of Images
Authors	Craig A. Glastonbury, Michael Ferlaino, Christoffer Nellåker, Cecilia M. Lindgren
Abstract	Biological imaging data are often partially confounded or contain unwanted variability. Examples of such phenomena include variable lighting across microscopy image captures, stain intensity variation in histological slides, and batch effects for high throughput drug screening assays. Therefore, to develop “fair” models which generalise well to unseen examples, it is crucial to learn data representations that are insensitive to nuisance factors of variation. In this paper, we present a strategy based on adversarial training, capable of learning unsupervised representations invariant to confounders. As an empirical validation of our method, we use deep convolutional autoencoders to learn unbiased cellular representations from microscopy imaging.
Tasks
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06498v2
PDF	http://arxiv.org/pdf/1811.06498v2.pdf
PWC	https://paperswithcode.com/paper/adjusting-for-confounding-in-unsupervised
Repo	https://github.com/Nellaker-group/FairUnsupervisedRepresentations
Framework	pytorch


Title	The Privacy Policy Landscape After the GDPR
Authors	Thomas Linden, Rishabh Khandelwal, Hamza Harkous, Kassem Fawaz
Abstract	The EU General Data Protection Regulation (GDPR) is one of the most demanding and comprehensive privacy regulations of all time. A year after it went into effect, we study its impact on the landscape of privacy policies online. We conduct the first longitudinal, in-depth, and at-scale assessment of privacy policies before and after the GDPR. We gauge the complete consumption cycle of these policies, from the first user impressions until the compliance assessment. We create a diverse corpus of two sets of 6,278 unique English-language privacy policies from inside and outside the EU, covering their pre-GDPR and the post-GDPR versions. The results of our tests and analyses suggest that the GDPR has been a catalyst for a major overhaul of the privacy policies inside and outside the EU. This overhaul of the policies, manifesting in extensive textual changes, especially for the EU-based websites, comes at mixed benefits to the users. While the privacy policies have become considerably longer, our user study with 470 participants on Amazon MTurk indicates a significant improvement in the visual representation of privacy policies from the users’ perspective for the EU websites. We further develop a new workflow for the automated assessment of requirements in privacy policies. Using this workflow, we show that privacy policies cover more data practices and are more consistent with seven compliance requirements post the GDPR. We also assess how transparent the organizations are with their privacy practices by performing specificity analysis. In this analysis, we find evidence for positive changes triggered by the GDPR, with the specificity level improving on average. Still, we find the landscape of privacy policies to be in a transitional phase; many policies still do not meet several key GDPR requirements or their improved coverage comes with reduced specificity.
Tasks
Published	2018-09-22
URL	https://arxiv.org/abs/1809.08396v3
PDF	https://arxiv.org/pdf/1809.08396v3.pdf
PWC	https://paperswithcode.com/paper/the-privacy-policy-landscape-after-the-gdpr
Repo	https://github.com/wi-pi/GDPR
Framework	none

A Kernel Perspective for Regularizing Deep Neural Networks


Title	A Kernel Perspective for Regularizing Deep Neural Networks
Authors	Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal
Abstract	We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS). Even though this norm cannot be computed, it admits upper and lower approximations leading to various practical strategies. Specifically, this perspective (i) provides a common umbrella for many existing regularization principles, including spectral norm and gradient penalties, or adversarial training, (ii) leads to new effective regularization penalties, and (iii) suggests hybrid strategies combining lower and upper bounds to get better approximations of the RKHS norm. We experimentally show this approach to be effective when learning on small datasets, or to obtain adversarially robust models.
Tasks
Published	2018-09-30
URL	https://arxiv.org/abs/1810.00363v4
PDF	https://arxiv.org/pdf/1810.00363v4.pdf
PWC	https://paperswithcode.com/paper/a-kernel-perspective-for-regularizing-deep
Repo	https://github.com/albietz/kernel_reg
Framework	pytorch

Meta-learning with differentiable closed-form solvers


Title	Meta-learning with differentiable closed-form solvers
Authors	Luca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi
Abstract	Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, such as nearest neighbours or gradient descent. Nonetheless, the machine learning literature contains a wealth of methods that learn non-deep models very efficiently. In this paper, we propose to use these fast convergent methods as the main adaptation mechanism for few-shot learning. The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data. This requires back-propagating errors through the solver steps. While normally the cost of the matrix operations involved in such a process would be significant, by using the Woodbury identity we can make the small number of examples work to our advantage. We propose both closed-form and iterative solvers, based on ridge regression and logistic regression components. Our methods constitute a simple and novel approach to the problem of few-shot learning and achieve performance competitive with or superior to the state of the art on three benchmarks.
Tasks	Few-Shot Learning, Meta-Learning
Published	2018-05-21
URL	https://arxiv.org/abs/1805.08136v3
PDF	https://arxiv.org/pdf/1805.08136v3.pdf
PWC	https://paperswithcode.com/paper/meta-learning-with-differentiable-closed-form
Repo	https://github.com/goldblum/AdversarialQuerying
Framework	pytorch