October 20, 2019

3116 words 15 mins read

Paper Group AWR 185

Classifying Online Dating Profiles on Tinder using FaceNet Facial Embeddings. Defining Locality for Surrogates in Post-hoc Interpretablity. Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms. DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Colo …

Classifying Online Dating Profiles on Tinder using FaceNet Facial Embeddings


Title	Classifying Online Dating Profiles on Tinder using FaceNet Facial Embeddings
Authors	Charles F Jekel, Raphael T. Haftka
Abstract	A method to produce personalized classification models to automatically review online dating profiles on Tinder is proposed, based on the user’s historical preference. The method takes advantage of a FaceNet facial classification model to extract features which may be related to facial attractiveness. The embeddings from a FaceNet model were used as the features to describe an individual’s face. A user reviewed 8,545 online dating profiles. For each reviewed online dating profile, a feature set was constructed from the profile images which contained just one face. Two approaches are presented to go from the set of features for each face, to a set of profile features. A simple logistic regression trained on the embeddings from just 20 profiles could obtain a 65% validation accuracy. A point of diminishing marginal returns was identified to occur around 80 profiles, at which the model accuracy of 73% would only improve marginally after reviewing a significant number of additional profiles.
Tasks
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04347v1
PDF	http://arxiv.org/pdf/1803.04347v1.pdf
PWC	https://paperswithcode.com/paper/classifying-online-dating-profiles-on-tinder
Repo	https://github.com/cjekel/tindetheus
Framework	tf

Defining Locality for Surrogates in Post-hoc Interpretablity


Title	Defining Locality for Surrogates in Post-hoc Interpretablity
Authors	Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
Abstract	Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.
Tasks
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07498v1
PDF	http://arxiv.org/pdf/1806.07498v1.pdf
PWC	https://paperswithcode.com/paper/defining-locality-for-surrogates-in-post-hoc
Repo	https://github.com/axadil/locality-interpretable-surrogate
Framework	none

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms


Title	Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Authors	Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, Lawrence Carin
Abstract	Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: (i) a max-pooling operation for improved interpretability; and (ii) a hierarchical pooling operation, which preserves spatial (n-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: (i) (long) document classification; (ii) text sequence matching; and (iii) short text tasks, including classification and tagging. The source code and datasets can be obtained from https:// github.com/dinghanshen/SWEM.
Tasks	Document Classification, Named Entity Recognition, Sentiment Analysis, Subjectivity Analysis, Text Classification, Word Embeddings
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09843v1
PDF	http://arxiv.org/pdf/1805.09843v1.pdf
PWC	https://paperswithcode.com/paper/baseline-needs-more-love-on-simple-word
Repo	https://github.com/nyk510/scdv-python
Framework	none

DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image


Title	DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image
Authors	Jiaxiong Qiu, Zhaopeng Cui, Yinda Zhang, Xingdi Zhang, Shuaicheng Liu, Bing Zeng, Marc Pollefeys
Abstract	In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates surface normals as the intermediate representation to produce dense depth, and can be trained end-to-end. With a modified encoder-decoder structure, our network effectively fuses the dense color image and the sparse LiDAR depth. To address outdoor specific challenges, our network predicts a confidence mask to handle mixed LiDAR signals near foreground boundaries due to occlusion, and combines estimates from the color image and surface normals with learned attention maps to improve the depth accuracy especially for distant areas. Extensive experiments demonstrate that our model improves upon the state-of-the-art performance on KITTI depth completion benchmark. Ablation study shows the positive impact of each model components to the final performance, and comprehensive analysis shows that our model generalizes well to the input with higher sparsity or from indoor scenes.
Tasks	Depth Completion, Depth Estimation
Published	2018-12-02
URL	http://arxiv.org/abs/1812.00488v2
PDF	http://arxiv.org/pdf/1812.00488v2.pdf
PWC	https://paperswithcode.com/paper/deeplidar-deep-surface-normal-guided-depth
Repo	https://github.com/JiaxiongQ/DeepLiDAR
Framework	pytorch

Adversarial Reprogramming of Text Classification Neural Networks


Title	Adversarial Reprogramming of Text Classification Neural Networks
Authors	Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar
Abstract	Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new classification task. While this reprogramming approach works for neural networks with a continuous input space such as that of images, it is not directly applicable to neural networks trained for tasks such as text classification, where the input space is discrete. Repurposing such classification networks would require the attacker to learn an adversarial program that maps inputs from one discrete space to the other. In this work, we introduce a context-based vocabulary remapping model to reprogram neural networks trained on a specific sequence classification task, for a new sequence classification task desired by the adversary. We propose training procedures for this adversarial program in both white-box and black-box settings. We demonstrate the application of our model by adversarially repurposing various text-classification models including LSTM, bi-directional LSTM and CNN for alternate classification tasks.
Tasks	Text Classification
Published	2018-09-06
URL	https://arxiv.org/abs/1809.01829v4
PDF	https://arxiv.org/pdf/1809.01829v4.pdf
PWC	https://paperswithcode.com/paper/adversarial-reprogramming-of-sequence
Repo	https://github.com/paarthneekhara/rnn_adversarial_reprogramming
Framework	pytorch

Updating the generator in PPGN-h with gradients flowing through the encoder


Title	Updating the generator in PPGN-h with gradients flowing through the encoder
Authors	Hesam Pakdaman
Abstract	The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially seem to belong to the real data distribution, and a discriminator which is to distinguish fake from genuine samples. The Noiseless Joint Plug & Play model offers an extension to the framework by simultaneously training autoencoders. This model uses a pre-trained encoder as a feature extractor, feeding the generator with global information. Using the Plug & Play network as baseline, we design a new model by adding discriminators to the Plug & Play architecture. These additional discriminators are trained to discern real and fake latent codes, which are the output of the encoder using genuine and generated inputs, respectively. We proceed to investigate whether this approach is viable. Experiments conducted for the MNIST manifold show that this indeed is the case.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00630v1
PDF	http://arxiv.org/pdf/1804.00630v1.pdf
PWC	https://paperswithcode.com/paper/updating-the-generator-in-ppgn-h-with
Repo	https://github.com/hesampakdaman/ppgn-disc
Framework	pytorch

Scaling Submodular Optimization Approaches for Control Applications in Networked Systems


Title	Scaling Submodular Optimization Approaches for Control Applications in Networked Systems
Authors	Arun V Sathanur
Abstract	Often times, in many design problems, there is a need to select a small set of informative or representative elements from a large ground set of entities in an optimal fashion. Submodular optimization that provides for a formal way to solve such problems, has recently received significant attention from the controls community where such subset selection problems are abound. However, scaling these approaches to large systems can be challenging because of the high computational complexity of the overall flow, in-part due to the high-complexity compute-oracles used to determine the objective function values. In this work, we explore a well-known paradigm, namely leader-selection in a multi-agent networked environment to illustrate strategies for scalable submodular optimization. We study the performance of the state-of-the-art stochastic and distributed greedy algorithms as well as explore techniques that accelerate the computation oracles within the optimization loop. We finally present results combining accelerated greedy algorithms with accelerated computation oracles and demonstrate significant speedups with little loss of optimality when compared to the baseline ordinary greedy algorithm.
Tasks
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02837v1
PDF	http://arxiv.org/pdf/1810.02837v1.pdf
PWC	https://paperswithcode.com/paper/scaling-submodular-optimization-approaches
Repo	https://github.com/arunsv/submodular
Framework	none

Taking Human out of Learning Applications: A Survey on Automated Machine Learning


Title	Taking Human out of Learning Applications: A Survey on Automated Machine Learning
Authors	Quanming Yao, Mengshuo Wang, Yuqiang Chen, Wenyuan Dai, Yu-Feng Li, Wei-Wei Tu, Qiang Yang, Yang Yu
Abstract	Machine learning techniques have deeply rooted in our everyday life. However, since it is knowledge- and labor-intensive to pursue good learning performance, human experts are heavily involved in every aspect of machine learning. In order to make machine learning techniques easier to apply and reduce the demand for experienced human experts, automated machine learning (AutoML) has emerged as a hot topic with both industrial and academic interest. In this paper, we provide an up to date survey on AutoML. First, we introduce and define the AutoML problem, with inspiration from both realms of automation and machine learning. Then, we propose a general AutoML framework that not only covers most existing approaches to date but also can guide the design for new methods. Subsequently, we categorize and review the existing works from two aspects, i.e., the problem setup and the employed techniques. Finally, we provide a detailed analysis of AutoML approaches and explain the reasons underneath their successful applications. We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future research.
Tasks	AutoML
Published	2018-10-31
URL	https://arxiv.org/abs/1810.13306v4
PDF	https://arxiv.org/pdf/1810.13306v4.pdf
PWC	https://paperswithcode.com/paper/taking-human-out-of-learning-applications-a
Repo	https://github.com/xiangning-chen/SIF
Framework	pytorch

An Empirical Study of Rich Subgroup Fairness for Machine Learning


Title	An Empirical Study of Rich Subgroup Fairness for Machine Learning
Authors	Michael Kearns, Seth Neel, Aaron Roth, Zhiwei Steven Wu
Abstract	Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent a fairness constraint. In this paper, we undertake an extensive empirical evaluation of the algorithm of Kearns et al. On four real datasets for which fairness is a concern, we investigate the basic convergence of the algorithm when instantiated with fast heuristics in place of learning oracles, measure the tradeoffs between fairness and accuracy, and compare this approach with the recent algorithm of Agarwal et al. [2018], which implements weaker and more traditional marginal fairness constraints defined by individual protected attributes. We find that in general, the Kearns et al. algorithm converges quickly, large gains in fairness can be obtained with mild costs to accuracy, and that optimizing accuracy subject only to marginal fairness leads to classifiers with substantial subgroup unfairness. We also provide a number of analyses and visualizations of the dynamics and behavior of the Kearns et al. algorithm. Overall we find this algorithm to be effective on real data, and rich subgroup fairness to be a viable notion in practice.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.08166v1
PDF	http://arxiv.org/pdf/1808.08166v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-study-of-rich-subgroup-fairness
Repo	https://github.com/SaeedSharifiMa/FairDP
Framework	none

Content-Based Citation Recommendation


Title	Content-Based Citation Recommendation
Authors	Chandra Bhagavatula, Sergey Feldman, Russell Power, Waleed Ammar
Abstract	We present a content-based method for recommending citations in an academic paper draft. We embed a given query document into a vector space, then use its nearest neighbors as candidates, and rerank the candidates using a discriminative model trained to distinguish between observed and unobserved citations. Unlike previous work, our method does not require metadata such as author names which can be missing, e.g., during the peer review process. Without using metadata, our method outperforms the best reported results on PubMed and DBLP datasets with relative improvements of over 18% in F1@20 and over 22% in MRR. We show empirically that, although adding metadata improves the performance on standard metrics, it favors self-citations which are less useful in a citation recommendation setup. We release an online portal (http://labs.semanticscholar.org/citeomatic/) for citation recommendation based on our method, and a new dataset OpenCorpus of 7 million research articles to facilitate future research on this task.
Tasks
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08301v1
PDF	http://arxiv.org/pdf/1802.08301v1.pdf
PWC	https://paperswithcode.com/paper/content-based-citation-recommendation
Repo	https://github.com/allenai/citeomatic
Framework	tf

Context-aware Deep Feature Compression for High-speed Visual Tracking


Title	Context-aware Deep Feature Compression for High-speed Visual Tracking
Authors	Jongwon Choi, Hyung Jin Chang, Tobias Fischer, Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi
Abstract	We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.
Tasks	Denoising, Visual Object Tracking, Visual Tracking
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10537v1
PDF	http://arxiv.org/pdf/1803.10537v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-deep-feature-compression-for
Repo	https://github.com/jongwon20000/TRACA
Framework	none

Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model


Title	Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model
Authors	Vered Shwartz, Chris Waterson
Abstract	Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.
Tasks
Published	2018-03-21
URL	http://arxiv.org/abs/1803.08073v1
PDF	http://arxiv.org/pdf/1803.08073v1.pdf
PWC	https://paperswithcode.com/paper/olive-oil-is-made-of-olives-baby-oil-is-made
Repo	https://github.com/tensorflow/models/tree/master/research/lexnet_nc
Framework	tf

Deep Segmentation and Registration in X-Ray Angiography Video


Title	Deep Segmentation and Registration in X-Ray Angiography Video
Authors	Athanasios Vlontzos, Krystian Mikolajczyk
Abstract	In interventional radiology, short video sequences of vein structure in motion are captured in order to help medical personnel identify vascular issues or plan intervention. Semantic segmentation can greatly improve the usefulness of these videos by indicating exact position of vessels and instruments, thus reducing the ambiguity. We propose a real-time segmentation method for these tasks, based on U-Net network trained in a Siamese architecture from automatically generated annotations. We make use of noisy low level binary segmentation and optical flow to generate multi class annotations that are successively improved in a multistage segmentation approach. We significantly improve the performance of a state of the art U-Net at the processing speeds of 90fps.
Tasks	Optical Flow Estimation, Semantic Segmentation
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06406v2
PDF	http://arxiv.org/pdf/1805.06406v2.pdf
PWC	https://paperswithcode.com/paper/deep-segmentation-and-registration-in-x-ray
Repo	https://github.com/thanosvlo/Deep-Segmentation-and-Registration-in-X-Ray-Angiography-Video
Framework	none

GuacaMol: Benchmarking Models for De Novo Molecular Design


Title	GuacaMol: Benchmarking Models for De Novo Molecular Design
Authors	Nathan Brown, Marco Fiscato, Marwin H. S. Segler, Alain C. Vaucher
Abstract	De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, models for molecular design based on neural networks appeared recently and show promising results. However, the new models have not been profiled on consistent tasks, and comparative studies to well-established algorithms have only seldom been performed. To standardize the assessment of both classical and neural models for de novo molecular design, we propose an evaluation framework, GuacaMol, based on a suite of standardized benchmarks. The benchmark tasks encompass measuring the fidelity of the models to reproduce the property distribution of the training sets, the ability to generate novel molecules, the exploration and exploitation of chemical space, and a variety of single and multi-objective optimization tasks. The benchmarking open-source Python code, and a leaderboard can be found on https://benevolent.ai/guacamol
Tasks	Drug Discovery
Published	2018-11-22
URL	http://arxiv.org/abs/1811.09621v2
PDF	http://arxiv.org/pdf/1811.09621v2.pdf
PWC	https://paperswithcode.com/paper/guacamol-benchmarking-models-for-de-novo
Repo	https://github.com/benevolentAI/guacamol_baselines
Framework	pytorch

ABC: A Big CAD Model Dataset For Geometric Deep Learning


Title	ABC: A Big CAD Model Dataset For Geometric Deep Learning
Authors	Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo
Abstract	We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows generating data in different formats and resolutions, enabling fair comparisons for a wide range of geometric learning algorithms. As a use case for our dataset, we perform a large-scale benchmark for estimation of surface normals, comparing existing data driven methods and evaluating their performance against both the ground truth and traditional normal estimation methods.
Tasks
Published	2018-12-15
URL	http://arxiv.org/abs/1812.06216v2
PDF	http://arxiv.org/pdf/1812.06216v2.pdf
PWC	https://paperswithcode.com/paper/abc-a-big-cad-model-dataset-for-geometric
Repo	https://github.com/yangyanli/PointCNN
Framework	tf