Paper Group AWR 320
Mend The Learning Approach, Not the Data: Insights for Ranking E-Commerce Products. Instagram Fake and Automated Account Detection. Disentangled Representation Learning for 3D Face Shape. Scalable Hierarchical Clustering with Tree Grafting. Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with …
Mend The Learning Approach, Not the Data: Insights for Ranking E-Commerce Products
| Title | Mend The Learning Approach, Not the Data: Insights for Ranking E-Commerce Products |
| Authors | Muhammad Umer Anwaar, Dmytro Rybalko, Martin Kleinsteuber |
| Abstract | Improved search quality enhances users’ satisfaction, which directly impacts sales growth of an E-Commerce (E-Com) platform. Traditional Learning to Rank (LTR) algorithms require relevance judgments on products. In E-Com, getting such judgments poses an immense challenge. In the literature, it is proposed to employ user feedback (add-to-basket (AtB) clicks, orders etc) to generate relevance judgments. It is done in two steps: first, query-product pair data are aggregated from the logs and then order rate etc are calculated for each pair in the logs. In this paper, we advocate counterfactual risk minimization (CRM) approach which circumvents the need of relevance judgements, data aggregation and is better suited for learning from logged data, i.e. contextual bandit feedback. Due to unavailability of public E-Com LTR dataset, we provide \textit{Commercial dataset} from our platform. It contains more than 10 million AtB click logs and 1 million order logs from a catalogue of about 3.5 million products associated with 3060 queries. To the best of our knowledge, this is the first work which examines effectiveness of CRM approach in learning ranking model from real-world logged data. Our empirical evaluation shows that our CRM approach learns effectively from logged data and beats a strong baseline ranker ($\lambda$-MART) by a huge margin. Our method outperforms full-information loss (e.g. cross-entropy) on various deep neural network models. These findings demonstrate that by adopting CRM approach, E-Com platforms can get better product search quality compared to full-information approach. The code and dataset can be accessed at: https://github.com/ecom-research/CRM-LTR. |
| Tasks | Learning-To-Rank |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10409v5 |
| https://arxiv.org/pdf/1907.10409v5.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-learning-from-logs-for |
| Repo | https://github.com/ecom-research/CRM_LTR |
| Framework | none |
Instagram Fake and Automated Account Detection
| Title | Instagram Fake and Automated Account Detection |
| Authors | Fatih Cagatay Akyon, Esat Kalfaoglu |
| Abstract | Fake engagement is one of the significant problems in Online Social Networks (OSNs) which is used to increase the popularity of an account in an inorganic manner. The detection of fake engagement is crucial because it leads to loss of money for businesses, wrong audience targeting in advertising, wrong product predictions systems, and unhealthy social network environment. This study is related with the detection of fake and automated accounts which leads to fake engagement on Instagram. Prior to this work, there were no publicly available dataset for fake and automated accounts. For this purpose, two datasets have been published for the detection of fake and automated accounts. For the detection of these accounts, machine learning algorithms like Naive Bayes, Logistic Regression, Support Vector Machines and Neural Networks are applied. Additionally, for the detection of automated accounts, cost sensitive genetic algorithm is proposed to handle the unnatural bias in the dataset. To deal with the unevenness problem in the fake dataset, Smote-nc algorithm is implemented. For the automated and fake account detection datasets, 86% and 96% classification accuracies are obtained, respectively. |
| Tasks | |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1910.03090v2 |
| https://arxiv.org/pdf/1910.03090v2.pdf | |
| PWC | https://paperswithcode.com/paper/instagram-fake-and-automated-account |
| Repo | https://github.com/fcakyon/instafake-dataset |
| Framework | none |
Disentangled Representation Learning for 3D Face Shape
| Title | Disentangled Representation Learning for 3D Face Shape |
| Authors | Zi-Hang Jiang, Qianyi Wu, Keyu Chen, Juyong Zhang |
| Abstract | In this paper, we present a novel strategy to design disentangled 3D face shape representation. Specifically, a given 3D face shape is decomposed into identity part and expression part, which are both encoded and decoded in a nonlinear way. To solve this problem, we propose an attribute decomposition framework for 3D face mesh. To better represent face shapes which are usually nonlinear deformed between each other, the face shapes are represented by a vertex based deformation representation rather than Euclidean coordinates. The experimental results demonstrate that our method has better performance than existing methods on decomposing the identity and expression parts. Moreover, more natural expression transfer results can be achieved with our method than existing methods. |
| Tasks | Representation Learning |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09887v2 |
| http://arxiv.org/pdf/1902.09887v2.pdf | |
| PWC | https://paperswithcode.com/paper/disentangled-representation-learning-for-3d |
| Repo | https://github.com/zihangJiang/DR-Learning-for-3D-Face |
| Framework | tf |
Scalable Hierarchical Clustering with Tree Grafting
| Title | Scalable Hierarchical Clustering with Tree Grafting |
| Authors | Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, Andrew McCallum |
| Abstract | We introduce Grinch, a new algorithm for large-scale, non-greedy hierarchical clustering with general linkage functions that compute arbitrary similarity between two point sets. The key components of Grinch are its rotate and graft subroutines that efficiently reconfigure the hierarchy as new points arrive, supporting discovery of clusters with complex structure. Grinch is motivated by a new notion of separability for clustering with linkage functions: we prove that when the model is consistent with a ground-truth clustering, Grinch is guaranteed to produce a cluster tree containing the ground-truth, independent of data arrival order. Our empirical results on benchmark and author coreference datasets (with standard and learned linkage functions) show that Grinch is more accurate than other scalable methods, and orders of magnitude faster than hierarchical agglomerative clustering. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00076v1 |
| https://arxiv.org/pdf/2001.00076v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-hierarchical-clustering-with-tree |
| Repo | https://github.com/iesl/grinch |
| Framework | none |
Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays
| Title | Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays |
| Authors | Ricardo Bigolin Lanfredi, Joyce D. Schroeder, Clement Vachet, Tolga Tasdizen |
| Abstract | Knowledge of what spatial elements of medical images deep learning methods use as evidence is important for model interpretability, trustiness, and validation. There is a lack of such techniques for models in regression tasks. We propose a method, called visualization for regression with a generative adversarial network (VR-GAN), for formulating adversarial training specifically for datasets containing regression target values characterizing disease severity. We use a conditional generative adversarial network where the generator attempts to learn to shift the output of a regressor through creating disease effect maps that are added to the original images. Meanwhile, the regressor is trained to predict the original regression value for the modified images. A model trained with this technique learns to provide visualization for how the image would appear at different stages of the disease. We analyze our method in a dataset of chest x-rays associated with pulmonary function tests, used for diagnosing chronic obstructive pulmonary disease (COPD). For validation, we compute the difference of two registered x-rays of the same patient at different time points and correlate it to the generated disease effect map. The proposed method outperforms a technique based on classification and provides realistic-looking images, making modifications to images following what radiologists usually observe for this disease. Implementation code is available at https://github.com/ricbl/vrgan. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10468v1 |
| https://arxiv.org/pdf/1908.10468v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-regression-training-for |
| Repo | https://github.com/ricbl/vrgan |
| Framework | pytorch |
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection
| Title | Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection |
| Authors | Nafise Sadat Moosavi, Leo Born, Massimo Poesio, Michael Strube |
| Abstract | The common practice in coreference resolution is to identify and evaluate the maximum span of mentions. The use of maximum spans tangles coreference evaluation with the challenges of mention boundary detection like prepositional phrase attachment. To address this problem, minimum spans are manually annotated in smaller corpora. However, this additional annotation is costly and therefore, this solution does not scale to large corpora. In this paper, we propose the MINA algorithm for automatically extracting minimum spans to benefit from minimum span evaluation in all corpora. We show that the extracted minimum spans by MINA are consistent with those that are manually annotated by experts. Our experiments show that using minimum spans is in particular important in cross-dataset coreference evaluation, in which detected mention boundaries are noisier due to domain shift. We will integrate MINA into https://github.com/ns-moosavi/coval for reporting standard coreference scores based on both maximum and automatically detected minimum spans. |
| Tasks | Boundary Detection, Coreference Resolution, Prepositional Phrase Attachment |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06703v1 |
| https://arxiv.org/pdf/1906.06703v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-automatically-extracted-minimum-spans |
| Repo | https://github.com/ns-moosavi/coval |
| Framework | none |
Deep learning tools for the measurement of animal behavior in neuroscience
| Title | Deep learning tools for the measurement of animal behavior in neuroscience |
| Authors | Mackenzie W. Mathis, Alexander Mathis |
| Abstract | Recent advances in computer vision have made accurate, fast and robust measurement of animal behavior a reality. In the past years powerful tools specifically designed to aid the measurement of behavior have come to fruition. Here we discuss how capturing the postures of animals - pose estimation - has been rapidly advancing with new deep learning methods. While challenges still remain, we envision that the fast-paced development of new deep learning tools will rapidly change the landscape of realizable real-world neuroscience. |
| Tasks | Pose Estimation |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13868v2 |
| https://arxiv.org/pdf/1909.13868v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-tools-for-the-measurement-of |
| Repo | https://github.com/AlexEMG/DeepLabCut |
| Framework | tf |
GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
| Title | GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition |
| Authors | Hui Chen, Zijia Lin, Guiguang Ding, Jianguang Lou, Yusen Zhang, Borje Karlsson |
| Abstract | The dominant approaches for named entity recognition (NER) mostly adopt complex recurrent neural networks (RNN), e.g., long-short-term-memory (LSTM). However, RNNs are limited by their recurrent nature in terms of computational efficiency. In contrast, convolutional neural networks (CNN) can fully exploit the GPU parallelism with their feedforward architectures. However, little attention has been paid to performing NER with CNNs, mainly owing to their difficulties in capturing the long-term context information in a sequence. In this paper, we propose a simple but effective CNN-based network for NER, i.e., gated relation network (GRN), which is more capable than common CNNs in capturing long-term context. Specifically, in GRN we firstly employ CNNs to explore the local context features of each word. Then we model the relations between words and use them as gates to fuse local context features into global ones for predicting labels. Without using recurrent layers that process a sentence in a sequential manner, our GRN allows computations to be performed in parallel across the entire sentence. Experiments on two benchmark NER datasets (i.e., CoNLL2003 and Ontonotes 5.0) show that, our proposed GRN can achieve state-of-the-art performance with or without external knowledge. It also enjoys lower time costs to train and test.We have made the code publicly available at https://github.com/HuiChen24/NER-GRN. |
| Tasks | Named Entity Recognition |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05611v2 |
| https://arxiv.org/pdf/1907.05611v2.pdf | |
| PWC | https://paperswithcode.com/paper/grn-gated-relation-network-to-enhance |
| Repo | https://github.com/HuiChen24/NER-GRN |
| Framework | pytorch |
xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
| Title | xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation |
| Authors | Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez |
| Abstract | Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of annotations in a new domain. There are many multi-modal datasets, but most UDA approaches are uni-modal. In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation. This is challenging as the two input spaces are heterogeneous and can be impacted differently by domain shift. In xMUDA, modalities learn from each other through mutual mimicking, disentangled from the segmentation objective, to prevent the stronger modality from adopting false predictions from the weaker one. We evaluate on new UDA scenarios including day-to-night, country-to-country and dataset-to-dataset, leveraging recent autonomous driving datasets. xMUDA brings large improvements over uni-modal UDA on all tested scenarios, and is complementary to state-of-the-art UDA techniques. Code is available at https://github.com/valeoai/xmuda. |
| Tasks | 3D Semantic Segmentation, Autonomous Driving, Domain Adaptation, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12676v2 |
| https://arxiv.org/pdf/1911.12676v2.pdf | |
| PWC | https://paperswithcode.com/paper/xmuda-cross-modal-unsupervised-domain |
| Repo | https://github.com/valeoai/xmuda |
| Framework | none |
Unsupervised State Representation Learning in Atari
| Title | Unsupervised State Representation Learning in Atari |
| Authors | Ankesh Anand, Evan Racah, Sherjil Ozair, Yoshua Bengio, Marc-Alexandre Côté, R Devon Hjelm |
| Abstract | State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision from rewards is a challenging open problem. We introduce a method that learns state representations by maximizing mutual information across spatially and temporally distinct features of a neural encoder of the observations. We also introduce a new benchmark based on Atari 2600 games where we evaluate representations based on how well they capture the ground truth state variables. We believe this new framework for evaluating representation learning models will be crucial for future representation learning research. Finally, we compare our technique with other state-of-the-art generative and contrastive representation learning methods. The code associated with this work is available at https://github.com/mila-iqia/atari-representation-learning |
| Tasks | Atari Games, Representation Learning |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08226v5 |
| https://arxiv.org/pdf/1906.08226v5.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-state-representation-learning-in |
| Repo | https://github.com/mila-iqia/atari-representation-learning |
| Framework | pytorch |
Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection
| Title | Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection |
| Authors | Samuel W. Remedios, Zihao Wu, Camilo Bermudez, Cailey I. Kerley, Snehashis Roy, Mayur B. Patel, John A. Butman, Bennett A. Landman, Dzung L. Pham |
| Abstract | Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to contain multiple instances. MIL is gaining traction for learning from weak labels but has not been widely applied to 3D medical imaging. MIL is well-suited to clinical CT acquisitions since (1) the highly anisotropic voxels hinder application of traditional 3D networks and (2) patch-based networks have limited ability to learn whole volume labels. In this work, we apply MIL with a deep convolutional neural network to identify whether clinical CT head image volumes possess one or more large hemorrhages (> 20cm$^3$), resulting in a learned 2D model without the need for 2D slice annotations. Individual image volumes are considered separate bags, and the slices in each volume are instances. Such a framework sets the stage for incorporating information obtained in clinical reports to help train a 2D segmentation approach. Within this context, we evaluate the data requirements to enable generalization of MIL by varying the amount of training data. Our results show that a training size of at least 400 patient image volumes was needed to achieve accurate per-slice hemorrhage detection. Over a five-fold cross-validation, the leading model, which made use of the maximum number of training volumes, had an average true positive rate of 98.10%, an average true negative rate of 99.36%, and an average precision of 0.9698. The models have been made available along with source code to enabled continued exploration and adaption of MIL in CT neuroimaging. |
| Tasks | Multiple Instance Learning |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05650v1 |
| https://arxiv.org/pdf/1911.05650v1.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-2d-weak-labels-from-volume-labels |
| Repo | https://github.com/sremedios/multiple_instance_learning |
| Framework | tf |
Learning Maximally Predictive Prototypes in Multiple Instance Learning
| Title | Learning Maximally Predictive Prototypes in Multiple Instance Learning |
| Authors | Mert Yuksekgonul, Ozgur Emre Sivrikaya, Mustafa Gokce Baydogan |
| Abstract | In this work, we propose a simple model that provides permutation invariant maximally predictive prototype generator from a given dataset, which leads to interpretability of the solution and concrete insights to the nature and the solution of a problem. Our aim is to find out prototypes in the feature space to map the collection of instances (i.e. bags) to a distance feature space and simultaneously learn a linear classifier for multiple instance learning (MIL). Our experiments on classical MIL benchmark datasets demonstrate that proposed framework is an accurate and efficient classifier compared to the existing approaches. |
| Tasks | Multiple Instance Learning |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.00965v2 |
| https://arxiv.org/pdf/1910.00965v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-maximally-predictive-prototypes-in |
| Repo | https://github.com/mertyg/learning-prototypes |
| Framework | pytorch |
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
| Title | Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration |
| Authors | Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, Devon Graham |
| Abstract | Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure (“Structured Procrastination”) that provably achieves near optimal performance with high probability and with nearly minimal runtime in the worst case. It also offers an $\textit{anytime}$ property: it keeps tightening its optimality guarantees the longer it is run. Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case. Follow-up work (“LeapsAndBounds”) achieves adaptivity but trades away the anytime property. This paper introduces a new algorithm, “Structured Procrastination with Confidence”, that preserves the near-optimality and anytime properties of Structured Procrastination while adding adaptivity. In particular, the new algorithm will perform dramatically faster in settings where many algorithm configurations perform poorly. We show empirically both that such settings arise frequently in practice and that the anytime property is useful for finding good configurations quickly. |
| Tasks | |
| Published | 2019-02-14 |
| URL | https://arxiv.org/abs/1902.05454v3 |
| https://arxiv.org/pdf/1902.05454v3.pdf | |
| PWC | https://paperswithcode.com/paper/procrastinating-with-confidence-near-optimal |
| Repo | https://github.com/drgrhm/alg_config |
| Framework | none |
Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling
| Title | Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling |
| Authors | Arka Daw, R. Quinn Thomas, Cayelan C. Carey, Jordan S. Read, Alison P. Appling, Anuj Karpatne |
| Abstract | To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture. This allows us to integrate such models with state of the art uncertainty estimation approaches such as Monte Carlo (MC) Dropout without sacrificing the physical consistency of our results. We demonstrate the effectiveness of our approach in ensuring better generalizability as well as physical consistency in MC estimates over data collected from Lake Mendota in Wisconsin and Falling Creek Reservoir in Virginia, even with limited training data. We further show that our MC estimates correctly match the distribution of ground-truth observations, thus making the PGA paradigm amenable to physically grounded uncertainty quantification. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02682v1 |
| https://arxiv.org/pdf/1911.02682v1.pdf | |
| PWC | https://paperswithcode.com/paper/physics-guided-architecture-pga-of-neural |
| Repo | https://github.com/arkadaw9/PGA_LSTM |
| Framework | none |
CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning
| Title | CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning |
| Authors | Yisroel Mirsky, Tom Mahler, Ilan Shelef, Yuval Elovici |
| Abstract | In 2018, clinics and hospitals were hit with numerous attacks leading to significant data breaches and interruptions in medical services. An attacker with access to medical records can do much more than hold the data for ransom or sell it on the black market. In this paper, we show how an attacker can use deep-learning to add or remove evidence of medical conditions from volumetric (3D) medical scans. An attacker may perform this act in order to stop a political candidate, sabotage research, commit insurance fraud, perform an act of terrorism, or even commit murder. We implement the attack using a 3D conditional GAN and show how the framework (CT-GAN) can be automated. Although the body is complex and 3D medical scans are very large, CT-GAN achieves realistic results which can be executed in milliseconds. To evaluate the attack, we focused on injecting and removing lung cancer from CT scans. We show how three expert radiologists and a state-of-the-art deep learning AI are highly susceptible to the attack. We also explore the attack surface of a modern radiology network and demonstrate one attack vector: we intercepted and manipulated CT scans in an active hospital network with a covert penetration test. Demo video: https://youtu.be/_mkRAArj-x0 Source code: https://github.com/ymirsky/CT-GAN |
| Tasks | |
| Published | 2019-01-11 |
| URL | https://arxiv.org/abs/1901.03597v3 |
| https://arxiv.org/pdf/1901.03597v3.pdf | |
| PWC | https://paperswithcode.com/paper/ct-gan-malicious-tampering-of-3d-medical |
| Repo | https://github.com/ymirsky/CT-GAN |
| Framework | tf |
