Paper Group ANR 1008
Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora. Equal Opportunity and Affirmative Action via Counterfactual Predictions. Kernel methods for detecting coherent structures in dynamical data. Improving localization-based approaches for breast cancer screening exam classification. Artific …
Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora
| Title | Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora |
| Authors | Marius Cătălin Iordan, Tyler Giallanza, Cameron T. Ellis, Nicole Beckage, Jonathan D. Cohen |
| Abstract | Understanding how human semantic knowledge is organized and how people use it to judge fundamental relationships, such as similarity between concepts, has proven difficult. Theoretical models have consistently failed to provide accurate predictions of human judgments, as has the application of machine learning algorithms to large-scale, text-based corpora (embedding spaces). Based on the hypothesis that context plays a critical role in human cognition, we show that generating embedding spaces using contextually-constrained text corpora greatly improves their ability to predict human judgments. Additionally, we introduce a novel context-based method for extracting interpretable feature information (e.g., size) from embedding spaces. Our findings suggest that contextually-constraining large-scale text corpora, coupled with applying state-of-the-art machine learning algorithms, may improve the correspondence between representations derived using such methods and those underlying human semantic structure. This promises to provide novel insight into human similarity judgments and designing algorithms that can interact effectively with human semantic knowledge. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06954v2 |
| https://arxiv.org/pdf/1910.06954v2.pdf | |
| PWC | https://paperswithcode.com/paper/context-matters-recovering-human-semantic |
| Repo | |
| Framework | |
Equal Opportunity and Affirmative Action via Counterfactual Predictions
| Title | Equal Opportunity and Affirmative Action via Counterfactual Predictions |
| Authors | Yixin Wang, Dhanya Sridhar, David M. Blei |
| Abstract | Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. In this paper, we propose two algorithms that adjust fitted ML predictors to make them fair. We focus on two legal notions of fairness: (a) providing equal opportunity (EO) to individuals regardless of sensitive attributes and (b) repairing historical disadvantages through affirmative action (AA). More technically, we produce fair EO and AA predictors by positing a causal model and considering counterfactual decisions. We prove that the resulting predictors are theoretically optimal in predictive performance while satisfying fairness. We evaluate the algorithms, and the trade-offs between accuracy and fairness, on datasets about admissions, income, credit and recidivism. |
| Tasks | Decision Making |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10870v2 |
| https://arxiv.org/pdf/1905.10870v2.pdf | |
| PWC | https://paperswithcode.com/paper/equal-opportunity-and-affirmative-action-via |
| Repo | |
| Framework | |
Kernel methods for detecting coherent structures in dynamical data
| Title | Kernel methods for detecting coherent structures in dynamical data |
| Authors | Stefan Klus, Brooke E. Husic, Mattes Mollenhauer, Frank Noé |
| Abstract | We illustrate relationships between classical kernel-based dimensionality reduction techniques and eigendecompositions of empirical estimates of reproducing kernel Hilbert space (RKHS) operators associated with dynamical systems. In particular, we show that kernel canonical correlation analysis (CCA) can be interpreted in terms of kernel transfer operators and that it can be obtained by optimizing the variational approach for Markov processes (VAMP) score. As a result, we show that coherent sets of particle trajectories can be computed by kernel CCA. We demonstrate the efficiency of this approach with several examples, namely the well-known Bickley jet, ocean drifter data, and a molecular dynamics problem with a time-dependent potential. Finally, we propose a straightforward generalization of dynamic mode decomposition (DMD) called coherent mode decomposition (CMD). Our results provide a generic machine learning approach to the computation of coherent sets with an objective score that can be used for cross-validation and the comparison of different methods. |
| Tasks | Dimensionality Reduction |
| Published | 2019-04-16 |
| URL | https://arxiv.org/abs/1904.07752v2 |
| https://arxiv.org/pdf/1904.07752v2.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-canonical-correlation-analysis |
| Repo | |
| Framework | |
Improving localization-based approaches for breast cancer screening exam classification
| Title | Improving localization-based approaches for breast cancer screening exam classification |
| Authors | Thibault Févry, Jason Phang, Nan Wu, S. Gene Kim, Linda Moy, Kyunghyun Cho, Krzysztof J. Geras |
| Abstract | We trained and evaluated a localization-based deep CNN for breast cancer screening exam classification on over 200,000 exams (over 1,000,000 images). Our model achieves an AUC of 0.919 in predicting malignancy in patients undergoing breast cancer screening, reducing the error rate of the baseline (Wu et al., 2019a) by 23%. In addition, the models generates bounding boxes for benign and malignant findings, providing interpretable predictions. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00615v1 |
| https://arxiv.org/pdf/1908.00615v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-localization-based-approaches-for |
| Repo | |
| Framework | |
Artificial intelligence empowered multi-AGVs in manufacturing systems
| Title | Artificial intelligence empowered multi-AGVs in manufacturing systems |
| Authors | Dong Li, Bo Ouyang, Duanpo Wu, Yaonan Wang |
| Abstract | AGVs are driverless robotic vehicles that picks up and delivers materials. How to improve the efficiency while preventing deadlocks is the core issue in designing AGV systems. In this paper, we propose an approach to tackle this problem.The proposed approach includes a traditional AGV scheduling algorithm, which aims at solving deadlock problems, and an artificial neural network based component, which predict future tasks of the AGV system, and make decisions on whether to send an AGV to the predicted starting location of the upcoming task,so as to save the time of waiting for an AGV to go to there first when the upcoming task is created. Simulation results show that the proposed method significantly improves the efficiency as against traditional method, up to 20% to 30%. |
| Tasks | |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03373v1 |
| https://arxiv.org/pdf/1909.03373v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-empowered-multi-agvs |
| Repo | |
| Framework | |
Time-Smoothed Gradients for Online Forecasting
| Title | Time-Smoothed Gradients for Online Forecasting |
| Authors | Tianhao Zhu, Sergul Aydore |
| Abstract | Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive to the selection of the learning parameter. Inspired by the local regret metric that we introduced previously, we propose to use time-smoothed gradients within SGD update. Using the public data set– GEFCom2014, we validate that our approach yields more stable results than the other existing approaches. Furthermore, we show that such a simple approach is computationally efficient compared to the alternatives. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08850v1 |
| https://arxiv.org/pdf/1905.08850v1.pdf | |
| PWC | https://paperswithcode.com/paper/time-smoothed-gradients-for-online |
| Repo | |
| Framework | |
Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?
| Title | Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing? |
| Authors | Michael Allan Ribers, Hannes Ullrich |
| Abstract | Antibiotic resistance constitutes a major health threat. Predicting bacterial causes of infections is key to reducing antibiotic misuse, a leading driver of antibiotic resistance. We train a machine learning algorithm on administrative and microbiological laboratory data from Denmark to predict diagnostic test outcomes for urinary tract infections. Based on predictions, we develop policies to improve prescribing in primary care, highlighting the relevance of physician expertise and policy implementation when patient distributions vary over time. The proposed policies delay antibiotic prescriptions for some patients until test results are known and give them instantly to others. We find that machine learning can reduce antibiotic use by 7.42 percent without reducing the number of treated bacterial infections. As Denmark is one of the most conservative countries in terms of antibiotic use, this result is likely to be a lower bound of what can be achieved elsewhere. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.03044v1 |
| https://arxiv.org/pdf/1906.03044v1.pdf | |
| PWC | https://paperswithcode.com/paper/battling-antibiotic-resistance-can-machine |
| Repo | |
| Framework | |
Cluster Regularized Quantization for Deep Networks Compression
| Title | Cluster Regularized Quantization for Deep Networks Compression |
| Authors | Yiming Hu, Jianquan Li, Xianlei Long, Shenhua Hu, Jiagang Zhu, Xingang Wang, Qingyi Gu |
| Abstract | Deep neural networks (DNNs) have achieved great success in a wide range of computer vision areas, but the applications to mobile devices is limited due to their high storage and computational cost. Much efforts have been devoted to compress DNNs. In this paper, we propose a simple yet effective method for deep networks compression, named Cluster Regularized Quantization (CRQ), which can reduce the presentation precision of a full-precision model to ternary values without significant accuracy drop. In particular, the proposed method aims at reducing the quantization error by introducing a cluster regularization term, which is imposed on the full-precision weights to enable them naturally concentrate around the target values. Through explicitly regularizing the weights during the re-training stage, the full-precision model can achieve the smooth transition to the low-bit one. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method. |
| Tasks | Quantization |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10370v1 |
| http://arxiv.org/pdf/1902.10370v1.pdf | |
| PWC | https://paperswithcode.com/paper/cluster-regularized-quantization-for-deep |
| Repo | |
| Framework | |
Image processing in DNA
| Title | Image processing in DNA |
| Authors | Chao Pan, S. M. Hossein Tabatabaei Yazdi, S Kasra Tabatabaei, Alvaro G. Hernandez, Charles Schroeder, Olgica Milenkovic |
| Abstract | The main obstacles for the practical deployment of DNA-based data storage platforms are the prohibitively high cost of synthetic DNA and the large number of errors introduced during synthesis. In particular, synthetic DNA products contain both individual oligo (fragment) symbol errors as well as missing DNA oligo errors, with rates that exceed those of modern storage systems by orders of magnitude. These errors can be corrected either through the use of a large number of redundant oligos or through cycles of writing, reading, and rewriting of information that eliminate the errors. Both approaches add to the overall storage cost and are hence undesirable. Here we propose the first method for storing quantized images in DNA that uses signal processing and machine learning techniques to deal with error and cost issues without resorting to the use of redundant oligos or rewriting. Our methods rely on decoupling the RGB channels of images, performing specialized quantization and compression on the individual color channels, and using new discoloration detection and image inpainting techniques. We demonstrate the performance of our approach experimentally on a collection of movie posters stored in DNA. |
| Tasks | Image Inpainting, Quantization |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10095v1 |
| https://arxiv.org/pdf/1910.10095v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-processing-in-dna |
| Repo | |
| Framework | |
ipA-MedGAN: Inpainting of Arbitrary Regions in Medical Imaging
| Title | ipA-MedGAN: Inpainting of Arbitrary Regions in Medical Imaging |
| Authors | Karim Armanious, Vijeth Kumar, Sherif Abdulatif, Tobias Hepp, Sergios Gatidis, Bin Yang |
| Abstract | Local deformations in medical modalities are common phenomena due to a multitude of factors such as metallic implants or limited field of views in magnetic resonance imaging (MRI). Completion of the missing or distorted regions is of special interest for automatic image analysis frameworks to enhance post-processing tasks such as segmentation or classification. In this work, we propose a new generative framework for medical image inpainting, titled ipA-MedGAN. It bypasses the limitations of previous frameworks by enabling inpainting of arbitrary shaped regions without a prior localization of the regions of interest. Thorough qualitative and quantitative comparisons with other inpainting and translational approaches have illustrated the superior performance of the proposed framework for the task of brain MR inpainting. |
| Tasks | Image Inpainting |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09230v2 |
| https://arxiv.org/pdf/1910.09230v2.pdf | |
| PWC | https://paperswithcode.com/paper/ipa-medgan-inpainting-of-arbitrarily-regions |
| Repo | |
| Framework | |
Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning
| Title | Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning |
| Authors | Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang, Xiaodan Liang, Liang Lin |
| Abstract | Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples. Leading approaches derived from meta-learning on images with a single visual object. Obfuscated by a complex background and multiple objects in one image, they are hard to promote the research of few-shot object detection/segmentation. In this work, we present a flexible and general methodology to achieve these tasks. Our work extends Faster /Mask R-CNN by proposing meta-learning over RoI (Region-of-Interest) features instead of a full image feature. This simple spirit disentangles multi-object information merged with the background, without bells and whistles, enabling Faster /Mask R-CNN turn into a meta-learner to achieve the tasks. Specifically, we introduce a Predictor-head Remodeling Network (PRN) that shares its main backbone with Faster /Mask R-CNN. PRN receives images containing few-shot objects with their bounding boxes or masks to infer their class attentive vectors. The vectors take channel-wise soft-attention on RoI features, remodeling those R-CNN predictor heads to detect or segment the objects that are consistent with the classes these vectors represent. In our experiments, Meta R-CNN yields the state of the art in few-shot object detection and improves few-shot object segmentation by Mask R-CNN. |
| Tasks | Few-Shot Learning, Few-Shot Object Detection, Meta-Learning, Object Detection, Semantic Segmentation |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13032v2 |
| https://arxiv.org/pdf/1909.13032v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-r-cnn-towards-general-solver-for |
| Repo | |
| Framework | |
Decoder Choice Network for Meta-Learning
| Title | Decoder Choice Network for Meta-Learning |
| Authors | Jialin Liu, Fei Chao, Longzhi Yang, Chih-Min Lin, Qiang Shen |
| Abstract | Meta-learning has been widely used for implementing few-shot learning and fast model adaptation. One kind of meta-learning methods attempt to learn how to control the gradient descent process in order to make the gradient-based learning have high speed and generalization. This work proposes a method that controls the gradient descent process of the model parameters of a neural network by limiting the model parameters in a low-dimensional latent space. The main challenge of this idea is that a decoder with too many parameters is required. This work designs a decoder with typical structure and shares a part of weights in the decoder to reduce the number of the required parameters. Besides, this work has introduced ensemble learning to work with the proposed approach for improving performance. The results show that the proposed approach is witnessed by the superior performance over the Omniglot classification and the miniImageNet classification tasks. |
| Tasks | Few-Shot Learning, Meta-Learning, Omniglot |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11446v2 |
| https://arxiv.org/pdf/1909.11446v2.pdf | |
| PWC | https://paperswithcode.com/paper/decoder-choice-network-for-meta-learning |
| Repo | |
| Framework | |
Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
| Title | Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion |
| Authors | Zihao Wang, Kwun Ping Lai, Piji Li, Lidong Bing, Wai Lam |
| Abstract | For large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations has been investigated. In this work, we further advocate that handling uncommon entities is inevitable when dealing with infrequent relations. Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions. We design a novel model to better extract key information from textual descriptions. Besides, we also develop a novel generative model in our framework to enhance the performance by generating extra triplets during the training stage. Experiments are conducted on two datasets from real-world KGs, and the results show that our framework outperforms previous methods when dealing with infrequent relations and their accompanying uncommon entities. |
| Tasks | Few-Shot Learning, Knowledge Graph Completion, Knowledge Graphs, Meta-Learning |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11359v1 |
| https://arxiv.org/pdf/1909.11359v1.pdf | |
| PWC | https://paperswithcode.com/paper/tackling-long-tailed-relations-and-uncommon |
| Repo | |
| Framework | |
Automatic ISP image quality tuning using non-linear optimization
| Title | Automatic ISP image quality tuning using non-linear optimization |
| Authors | Jun Nishimura, Timo Gerasimow, Sushma Rao, Aleksandar Sutic, Chyuan-Tyng Wu, Gilad Michael |
| Abstract | Image Signal Processor (ISP) comprises of various blocks to reconstruct image sensor raw data to final image consumed by human visual system or computer vision applications. Each block typically has many tuning parameters due to the complexity of the operation. These need to be hand tuned by Image Quality (IQ) experts, which takes considerable amount of time. In this paper, we present an automatic IQ tuning using nonlinear optimization and automatic reference generation algorithms. The proposed method can produce high quality IQ in minutes as compared with weeks of hand-tuned results by IQ experts. In addition, the proposed method can work with any algorithms without being aware of their specific implementation. It was found successful on multiple different processing blocks such as noise reduction, demosaic, and sharpening. |
| Tasks | |
| Published | 2019-02-24 |
| URL | http://arxiv.org/abs/1902.09023v1 |
| http://arxiv.org/pdf/1902.09023v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-isp-image-quality-tuning-using-non |
| Repo | |
| Framework | |
A Theoretical Analysis of the Number of Shots in Few-Shot Learning
| Title | A Theoretical Analysis of the Number of Shots in Few-Shot Learning |
| Authors | Tianshi Cao, Marc Law, Sanja Fidler |
| Abstract | Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one used in meta-testing to obtain the best performance. We introduce a theoretical analysis of the impact of the shot number on Prototypical Networks, a state-of-the-art few-shot classification method. From our analysis, we propose a simple method that is robust to the choice of shot number used during meta-training, which is a crucial hyperparameter. The performance of our model trained for an arbitrary meta-training shot number shows great performance for different values of meta-testing shot numbers. We experimentally demonstrate our approach on different few-shot classification benchmarks. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11722v2 |
| https://arxiv.org/pdf/1909.11722v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-theoretical-analysis-of-the-number-of-shots |
| Repo | |
| Framework | |
