Paper Group AWR 360
A Multi-level procedure for enhancing accuracy of machine learning algorithms. Template-free Data-to-Text Generation of Finnish Sports News. On the (In)fidelity and Sensitivity for Explanations. Regression Concept Vectors for Bidirectional Explanations in Histopathology. ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks. BMN: Boun …
A Multi-level procedure for enhancing accuracy of machine learning algorithms
| Title | A Multi-level procedure for enhancing accuracy of machine learning algorithms |
| Authors | Kjetil O. Lye, Siddhartha Mishra, Roberto Molinaro |
| Abstract | We propose a multi-level method to increase the accuracy of machine learning algorithms for approximating observables in scientific computing, particularly those that arise in systems modeled by differential equations. The algorithm relies on judiciously combining a large number of computationally cheap training data on coarse resolutions with a few expensive training samples on fine grid resolutions. Theoretical arguments for lowering the generalization error, based on reducing the variance of the underlying maps, are provided and numerical evidence, indicating significant gains over underlying single-level machine learning algorithms, are presented. Moreover, we also apply the multi-level algorithm in the context of forward uncertainty quantification and observe a considerable speed-up over competing algorithms. |
| Tasks | |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09448v1 |
| https://arxiv.org/pdf/1909.09448v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-level-procedure-for-enhancing |
| Repo | https://github.com/mroberto166/MultilevelMachineLearning |
| Framework | tf |
Template-free Data-to-Text Generation of Finnish Sports News
| Title | Template-free Data-to-Text Generation of Finnish Sports News |
| Authors | Jenna Kanerva, Samuel Rönnqvist, Riina Kekki, Tapio Salakoski, Filip Ginter |
| Abstract | News articles such as sports game reports are often thought to closely follow the underlying game statistics, but in practice they contain a notable amount of background knowledge, interpretation, insight into the game, and quotes that are not present in the official statistics. This poses a challenge for automated data-to-text news generation with real-world news corpora as training data. We report on the development of a corpus of Finnish ice hockey news, edited to be suitable for training of end-to-end news generation methods, as well as demonstrate generation of text, which was judged by journalists to be relatively close to a viable product. The new dataset and system source code are available for research purposes at https://github.com/scoopmatic/finnish-hockey-news-generation-paper. |
| Tasks | Data-to-Text Generation, News Generation, Text Generation |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.01863v1 |
| https://arxiv.org/pdf/1910.01863v1.pdf | |
| PWC | https://paperswithcode.com/paper/template-free-data-to-text-generation-of |
| Repo | https://github.com/scoopmatic/finnish-hockey-news-generation-paper |
| Framework | none |
On the (In)fidelity and Sensitivity for Explanations
| Title | On the (In)fidelity and Sensitivity for Explanations |
| Authors | Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David I. Inouye, Pradeep Ravikumar |
| Abstract | We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods. By varying the perturbation distribution that defines infidelity, we obtain novel explanations by optimizing infidelity, which we show to out-perform existing explanations in both quantitative and qualitative measurements. Another salient question given these measures is how to modify any given explanation to have better values with respect to these measures. We propose a simple modification based on lowering sensitivity, and moreover show that when done appropriately, we could simultaneously improve both sensitivity as well as fidelity. |
| Tasks | |
| Published | 2019-01-27 |
| URL | https://arxiv.org/abs/1901.09392v4 |
| https://arxiv.org/pdf/1901.09392v4.pdf | |
| PWC | https://paperswithcode.com/paper/how-sensitive-are-sensitivity-based |
| Repo | https://github.com/chihkuanyeh/saliency_evaluation |
| Framework | pytorch |
Regression Concept Vectors for Bidirectional Explanations in Histopathology
| Title | Regression Concept Vectors for Bidirectional Explanations in Histopathology |
| Authors | Mara Graziani, Vincent Andrearczyk, Henning Müller |
| Abstract | Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in the activation space of a layer. The directional derivative of the decision function along the RCVs represents the network sensitivity to increasing values of a given concept measure. When applied to breast cancer grading, nuclei texture emerges as a relevant concept in the detection of tumor tissue in breast lymph node samples. We evaluate score robustness and consistency by statistical analysis. |
| Tasks | Breast Cancer Detection, Breast Cancer Histology Image Classification, Decision Making, Histopathological Image Classification |
| Published | 2019-04-09 |
| URL | http://arxiv.org/abs/1904.04520v1 |
| http://arxiv.org/pdf/1904.04520v1.pdf | |
| PWC | https://paperswithcode.com/paper/regression-concept-vectors-for-bidirectional |
| Repo | https://github.com/medgift/iMIMIC-RCVs |
| Framework | tf |
ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks
| Title | ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks |
| Authors | Cheng-I Lai, Nanxin Chen, Jesús Villalba, Najim Dehak |
| Abstract | We present JHU’s system submission to the ASVspoof 2019 Challenge: Anti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT). Anti-spoofing has gathered more and more attention since the inauguration of the ASVspoof Challenges, and ASVspoof 2019 dedicates to address attacks from all three major types: text-to-speech, voice conversion, and replay. Built upon previous research work on Deep Neural Network (DNN), ASSERT is a pipeline for DNN-based approach to anti-spoofing. ASSERT has four components: feature engineering, DNN models, network optimization and system combination, where the DNN models are variants of squeeze-excitation and residual networks. We conducted an ablation study of the effectiveness of each component on the ASVspoof 2019 corpus, and experimental results showed that ASSERT obtained more than 93% and 17% relative improvements over the baseline systems in the two sub-challenges in ASVspooof 2019, ranking ASSERT one of the top performing systems. Code and pretrained models will be made publicly available. |
| Tasks | Feature Engineering, Voice Conversion |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.01120v1 |
| http://arxiv.org/pdf/1904.01120v1.pdf | |
| PWC | https://paperswithcode.com/paper/assert-anti-spoofing-with-squeeze-excitation |
| Repo | https://github.com/jefflai108/ASSERT |
| Framework | pytorch |
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
| Title | BMN: Boundary-Matching Network for Temporal Action Proposal Generation |
| Authors | Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen |
| Abstract | Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve state-of-the-art temporal action detection performance. |
| Tasks | Action Detection, Temporal Action Localization, Temporal Action Proposal Generation |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09702v1 |
| https://arxiv.org/pdf/1907.09702v1.pdf | |
| PWC | https://paperswithcode.com/paper/bmn-boundary-matching-network-for-temporal |
| Repo | https://github.com/PaddlePaddle/models/tree/develop/dygraph/bmn |
| Framework | none |
Fast Low-rank Metric Learning for Large-scale and High-dimensional Data
| Title | Fast Low-rank Metric Learning for Large-scale and High-dimensional Data |
| Authors | Han Liu, Zhizhong Han, Yu-Shen Liu, Ming Gu |
| Abstract | Low-rank metric learning aims to learn better discrimination of data subject to low-rank constraints. It keeps the intrinsic low-rank structure of datasets and reduces the time cost and memory usage in metric learning. However, it is still a challenge for current methods to handle datasets with both high dimensions and large numbers of samples. To address this issue, we present a novel fast low-rank metric learning (FLRML) method.FLRML casts the low-rank metric learning problem into an unconstrained optimization on the Stiefel manifold, which can be efficiently solved by searching along the descent curves of the manifold.FLRML significantly reduces the complexity and memory usage in optimization, which makes the method scalable to both high dimensions and large numbers of samples.Furthermore, we introduce a mini-batch version of FLRML to make the method scalable to larger datasets which are hard to be loaded and decomposed in limited memory. The outperforming experimental results show that our method is with high accuracy and much faster than the state-of-the-art methods under several benchmarks with large numbers of high-dimensional data. Code has been made available at https://github.com/highan911/FLRML |
| Tasks | Metric Learning |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06297v1 |
| https://arxiv.org/pdf/1909.06297v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-low-rank-metric-learning-for-large-scale |
| Repo | https://github.com/highan911/FLRML |
| Framework | none |
Representation Learning for Attributed Multiplex Heterogeneous Network
| Title | Representation Learning for Attributed Multiplex Heterogeneous Network |
| Authors | Yukuo Cen, Xu Zou, Jianwei Zhang, Hongxia Yang, Jingren Zhou, Jie Tang |
| Abstract | Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist of billions of nodes and edges of multiple types, and each node is associated with different attributes. In this paper, we formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. The framework supports both transductive and inductive learning. We also give the theoretical analysis of the proposed framework, showing its connection with previous works and proving its better expressiveness. We conduct systematical evaluations for the proposed framework on four different genres of challenging datasets: Amazon, YouTube, Twitter, and Alibaba. Experimental results demonstrate that with the learned embeddings from the proposed framework, we can achieve statistically significant improvements (e.g., 5.99-28.23% lift by F1 scores; p«0.01, t-test) over previous state-of-the-art methods for link prediction. The framework has also been successfully deployed on the recommendation system of a worldwide leading e-commerce company, Alibaba Group. Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice. |
| Tasks | Graph Embedding, Link Prediction, Network Embedding, Product Recommendation, Representation Learning |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01669v2 |
| https://arxiv.org/pdf/1905.01669v2.pdf | |
| PWC | https://paperswithcode.com/paper/190501669 |
| Repo | https://github.com/cenyk1230/GATNE |
| Framework | tf |
On the design of convolutional neural networks for automatic detection of Alzheimer’s disease
| Title | On the design of convolutional neural networks for automatic detection of Alzheimer’s disease |
| Authors | Sheng Liu, Chhavi Yadav, Carlos Fernandez-Granda, Narges Razavian |
| Abstract | Early detection is a crucial goal in the study of Alzheimer’s Disease (AD). In this work, we describe several techniques to boost the performance of 3D convolutional neural networks trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an increment of approximately 14% in test accuracy over existing models when distinguishing between patients with AD, mild cognitive impairment, and controls in the ADNI dataset. Similar performance is achieved on an independent dataset. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03740v2 |
| https://arxiv.org/pdf/1911.03740v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-design-of-convolutional-neural |
| Repo | https://github.com/NYUMedML/CNN_design_for_AD |
| Framework | pytorch |
DALS: Deep Active Lesion Segmentation
| Title | DALS: Deep Active Lesion Segmentation |
| Authors | Ali Hatamizadeh, Assaf Hoogi, Debleena Sengupta, Wuyue Lu, Brian Wilcox, Daniel Rubin, Demetri Terzopoulos |
| Abstract | Lesion segmentation is an important problem in computer-assisted diagnosis that remains challenging due to the prevalence of low contrast, irregular boundaries that are unamenable to shape priors. We introduce Deep Active Lesion Segmentation (DALS), a fully automated segmentation framework for that leverages the powerful nonlinear feature extraction abilities of fully Convolutional Neural Networks (CNNs) and the precise boundary delineation abilities of Active Contour Models (ACMs). Our DALS framework benefits from an improved level-set ACM formulation with a per-pixel-parameterized energy functional and a novel multiscale encoder-decoder CNN that learns an initialization probability map along with parameter maps for the ACM. We evaluate our lesion segmentation model on a new Multiorgan Lesion Segmentation (MLS) dataset that contains images of various organs, including brain, liver, and lung, across different imaging modalities—MR and CT. Our results demonstrate favorable performance compared to competing methods, especially for small training datasets. |
| Tasks | Lesion Segmentation |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06933v3 |
| https://arxiv.org/pdf/1908.06933v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-active-lesion-segmentation |
| Repo | https://github.com/ahatamiz/DALS |
| Framework | none |
Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution
| Title | Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution |
| Authors | Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto, Dmitry Vetrov |
| Abstract | Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates. Modern variance reduction techniques mostly consider categorical distributions and have limited applicability when the number of possible outcomes becomes large. In this work, we consider models with latent permutations and propose control variates for the Plackett-Luce distribution. In particular, the control variates allow us to optimize black-box functions over permutations using stochastic gradient descent. To illustrate the approach, we consider a variety of causal structure learning tasks for continuous and discrete data. We show that our method outperforms competitive relaxation-based optimization methods and is also applicable to non-differentiable score functions. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10036v1 |
| https://arxiv.org/pdf/1911.10036v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-variance-black-box-gradient-estimates-for |
| Repo | https://github.com/agadetsky/pytorch-pl-variance-reduction |
| Framework | pytorch |
Transfer learning in hybrid classical-quantum neural networks
| Title | Transfer learning in hybrid classical-quantum neural networks |
| Authors | Andrea Mari, Thomas R. Bromley, Josh Izaac, Maria Schuld, Nathan Killoran |
| Abstract | We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti. |
| Tasks | Transfer Learning |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08278v1 |
| https://arxiv.org/pdf/1912.08278v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-in-hybrid-classical-quantum |
| Repo | https://github.com/XanaduAI/quantum-transfer-learning |
| Framework | pytorch |
Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach
| Title | Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach |
| Authors | Proteek Chandan Roy, Vishnu Naresh Boddeti |
| Abstract | Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images. As we witness the wide spread adoption of these systems, it is imperative to consider the problem of unintended leakage of information from an image representation, which might compromise the privacy of the data owner. This paper investigates the problem of learning an image representation that minimizes such leakage of user information. We formulate the problem as an adversarial non-zero sum game of finding a good embedding function with two competing goals: to retain as much task dependent discriminative image information as possible, while simultaneously minimizing the amount of information, as measured by entropy, about other sensitive attributes of the user. We analyze the stability and convergence dynamics of the proposed formulation using tools from non-linear systems theory and compare to that of the corresponding adversarial zero-sum game formulation that optimizes likelihood as a measure of information content. Numerical experiments on UCI, Extended Yale B, CIFAR-10 and CIFAR-100 datasets indicate that our proposed approach is able to learn image representations that exhibit high task performance while mitigating leakage of predefined sensitive information. |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05514v1 |
| http://arxiv.org/pdf/1904.05514v1.pdf | |
| PWC | https://paperswithcode.com/paper/mitigating-information-leakage-in-image |
| Repo | https://github.com/human-analysis/MaxEnt-ARL |
| Framework | pytorch |
Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization
| Title | Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization |
| Authors | Miika Aittala, Prafull Sharma, Lukas Murmann, Adam B. Yedidia, Gregory W. Wornell, William T. Freeman, Fredo Durand |
| Abstract | We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region. We solve this problem by factoring the observed video into a matrix product between the unknown hidden scene video and an unknown light transport matrix. This task is extremely ill-posed, as any non-negative factorization will satisfy the data. Inspired by recent work on the Deep Image Prior, we parameterize the factor matrices using randomly initialized convolutional neural networks trained in a one-off manner, and show that this results in decompositions that reflect the true motion in the hidden scene. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02314v1 |
| https://arxiv.org/pdf/1912.02314v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-mirrors-blind-inverse-light-1 |
| Repo | https://github.com/prafull7/compmirrors |
| Framework | pytorch |
dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance
| Title | dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance |
| Authors | Jo Schlemper, Ilkay Oksuz, James R. Clough, Jinming Duan, Andrew P. King, Julia A. Schnabel, Joseph V. Hajnal, Daniel Rueckert |
| Abstract | AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters. |
| Tasks | |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10995v2 |
| https://arxiv.org/pdf/1909.10995v2.pdf | |
| PWC | https://paperswithcode.com/paper/dautomap-decomposing-automap-to-achieve |
| Repo | https://github.com/js3611/dAUTOMAP |
| Framework | pytorch |
