Paper Group ANR 32
DeepSF: deep convolutional neural network for mapping protein sequences to folds. Improving One-Shot Learning through Fusing Side Information. A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop. Estimating prediction error for complex samples. Dynamic Label Graph Matching for Unsupervised Video …
DeepSF: deep convolutional neural network for mapping protein sequences to folds
| Title | DeepSF: deep convolutional neural network for mapping protein sequences to folds |
| Authors | Jie Hou, Badri Adhikari, Jianlin Cheng |
| Abstract | Motivation Protein fold recognition is an important problem in structural bioinformatics. Almost all traditional fold recognition methods use sequence (homology) comparison to indirectly predict the fold of a tar get protein based on the fold of a template protein with known structure, which cannot explain the relationship between sequence and fold. Only a few methods had been developed to classify protein sequences into a small number of folds due to methodological limitations, which are not generally useful in practice. Results We develop a deep 1D-convolution neural network (DeepSF) to directly classify any protein se quence into one of 1195 known folds, which is useful for both fold recognition and the study of se quence-structure relationship. Different from traditional sequence alignment (comparison) based methods, our method automatically extracts fold-related features from a protein sequence of any length and map it to the fold space. We train and test our method on the datasets curated from SCOP1.75, yielding a classification accuracy of 80.4%. On the independent testing dataset curated from SCOP2.06, the classification accuracy is 77.0%. We compare our method with a top profile profile alignment method - HHSearch on hard template-based and template-free modeling targets of CASP9-12 in terms of fold recognition accuracy. The accuracy of our method is 14.5%-29.1% higher than HHSearch on template-free modeling targets and 4.5%-16.7% higher on hard template-based modeling targets for top 1, 5, and 10 predicted folds. The hidden features extracted from sequence by our method is robust against sequence mutation, insertion, deletion and truncation, and can be used for other protein pattern recognition problems such as protein clustering, comparison and ranking. |
| Tasks | |
| Published | 2017-06-04 |
| URL | http://arxiv.org/abs/1706.01010v1 |
| http://arxiv.org/pdf/1706.01010v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepsf-deep-convolutional-neural-network-for |
| Repo | |
| Framework | |
Improving One-Shot Learning through Fusing Side Information
| Title | Improving One-Shot Learning through Fusing Side Information |
| Authors | Yao-Hung Hubert Tsai, Ruslan Salakhutdinov |
| Abstract | Deep Neural Networks (DNNs) often struggle with one-shot learning where we have only one or a few labeled training examples per category. In this paper, we argue that by using side information, we may compensate the missing information across classes. We introduce two statistical approaches for fusing side information into data representation learning to improve one-shot learning. First, we propose to enforce the statistical dependency between data representations and multiple types of side information. Second, we introduce an attention mechanism to efficiently treat examples belonging to the ‘lots-of-examples’ classes as quasi-samples (additional training samples) for ‘one-example’ classes. We empirically show that our learning architecture improves over traditional softmax regression networks as well as state-of-the-art attentional regression networks on one-shot recognition tasks. |
| Tasks | One-Shot Learning, Representation Learning |
| Published | 2017-10-23 |
| URL | http://arxiv.org/abs/1710.08347v2 |
| http://arxiv.org/pdf/1710.08347v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-one-shot-learning-through-fusing |
| Repo | |
| Framework | |
A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop
| Title | A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop |
| Authors | Andreas Holzinger, Markus Plass, Katharina Holzinger, Gloria Cerasela Crisan, Camelia-M. Pintea, Vasile Palade |
| Abstract | The goal of Machine Learning to automatically learn from data, extract knowledge and to make decisions without any human intervention. Such automatic (aML) approaches show impressive success. Recent results even demonstrate intriguingly that deep learning applied for automatic classification of skin lesions is on par with the performance of dermatologists, yet outperforms the average. As human perception is inherently limited, such approaches can discover patterns, e.g. that two objects are similar, in arbitrarily high-dimensional spaces what no human is able to do. Humans can deal only with limited amounts of data, whilst big data is beneficial for aML; however, in health informatics, we are often confronted with a small number of data sets, where aML suffer of insufficient training samples and many problems are computationally hard. Here, interactive machine learning (iML) may be of help, where a human-in-the-loop contributes to reduce the complexity of NP-hard problems. A further motivation for iML is that standard black-box approaches lack transparency, hence do not foster trust and acceptance of ML among end-users. Rising legal and privacy aspects, e.g. with the new European General Data Protection Regulations, make black-box approaches difficult to use, because they often are not able to explain why a decision has been made. In this paper, we present some experiments to demonstrate the effectiveness of the human-in-the-loop approach, particularly in opening the black-box to a glass-box and thus enabling a human directly to interact with an learning algorithm. We selected the Ant Colony Optimization framework, and applied it on the Traveling Salesman Problem, which is a good example, due to its relevance for health informatics, e.g. for the study of protein folding. From studies of how humans extract so much from so little data, fundamental ML-research also may benefit. |
| Tasks | |
| Published | 2017-08-03 |
| URL | http://arxiv.org/abs/1708.01104v1 |
| http://arxiv.org/pdf/1708.01104v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-glass-box-interactive-machine-learning |
| Repo | |
| Framework | |
Estimating prediction error for complex samples
| Title | Estimating prediction error for complex samples |
| Authors | Andrew Holbrook, Thomas Lumley, Daniel Gillen |
| Abstract | With a growing interest in using non-representative samples to train prediction models for numerous outcomes it is necessary to account for the sampling design that gives rise to the data in order to assess the generalized predictive utility of a proposed prediction rule. After learning a prediction rule based on a non-uniform sample, it is of interest to estimate the rule’s error rate when applied to unobserved members of the population. Efron (1986) proposed a general class of covariance penalty inflated prediction error estimators that assume the available training data are representative of the target population for which the prediction rule is to be applied. We extend Efron’s estimator to the complex sample context by incorporating Horvitz-Thompson sampling weights and show that it is consistent for the true generalization error rate when applied to the underlying superpopulation. The resulting Horvitz-Thompson-Efron (HTE) estimator is equivalent to dAIC, a recent extension of AIC to survey sampling data, but is more widely applicable. The proposed methodology is assessed with simulations and is applied to models predicting renal function obtained from the large-scale NHANES survey. |
| Tasks | |
| Published | 2017-11-13 |
| URL | https://arxiv.org/abs/1711.04877v3 |
| https://arxiv.org/pdf/1711.04877v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-prediction-error-for-complex |
| Repo | |
| Framework | |
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
| Title | Dynamic Label Graph Matching for Unsupervised Video Re-Identification |
| Authors | Mang Ye, Andy J Ma, Liang Zheng, Jiawei Li, P C Yuen |
| Abstract | Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods. |
| Tasks | Graph Matching, Person Re-Identification, Unsupervised Person Re-Identification |
| Published | 2017-09-27 |
| URL | http://arxiv.org/abs/1709.09297v1 |
| http://arxiv.org/pdf/1709.09297v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-label-graph-matching-for-unsupervised |
| Repo | |
| Framework | |
Generative Poisoning Attack Method Against Neural Networks
| Title | Generative Poisoning Attack Method Against Neural Networks |
| Authors | Chaofei Yang, Qing Wu, Hai Li, Yiran Chen |
| Abstract | Poisoning attack is identified as a severe security threat to machine learning algorithms. In many applications, for example, deep neural network (DNN) models collect public data as the inputs to perform re-training, where the input data can be poisoned. Although poisoning attack against support vector machines (SVM) has been extensively studied before, there is still very limited knowledge about how such attack can be implemented on neural networks (NN), especially DNNs. In this work, we first examine the possibility of applying traditional gradient-based method (named as the direct gradient method) to generate poisoned data against NNs by leveraging the gradient of the target model w.r.t. the normal data. We then propose a generative method to accelerate the generation rate of the poisoned data: an auto-encoder (generator) used to generate poisoned data is updated by a reward function of the loss, and the target NN model (discriminator) receives the poisoned data to calculate the loss w.r.t. the normal data. Our experiment results show that the generative method can speed up the poisoned data generation rate by up to 239.38x compared with the direct gradient method, with slightly lower model accuracy degradation. A countermeasure is also designed to detect such poisoning attack methods by checking the loss of the target model. |
| Tasks | |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01340v1 |
| http://arxiv.org/pdf/1703.01340v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-poisoning-attack-method-against |
| Repo | |
| Framework | |
DeepFense: Online Accelerated Defense Against Adversarial Deep Learning
| Title | DeepFense: Online Accelerated Defense Against Adversarial Deep Learning |
| Authors | Bita Darvish Rouhani, Mohammad Samragh, Mojan Javaheripi, Tara Javidi, Farinaz Koushanfar |
| Abstract | Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, online detection of malicious inputs is of utmost importance. We propose DeepFense, the first end-to-end automated framework that simultaneously enables efficient and safe execution of DL models. DeepFense formalizes the goal of thwarting adversarial attacks as an optimization problem that minimizes the rarely observed regions in the latent feature space spanned by a DL network. To solve the aforementioned minimization problem, a set of complementary but disjoint modular redundancies are trained to validate the legitimacy of the input samples in parallel with the victim DL model. DeepFense leverages hardware/software/algorithm co-design and customized acceleration to achieve just-in-time performance in resource-constrained settings. The proposed countermeasure is unsupervised, meaning that no adversarial sample is leveraged to train modular redundancies. We further provide an accompanying API to reduce the non-recurring engineering cost and ensure automated adaptation to various platforms. Extensive evaluations on FPGAs and GPUs demonstrate up to two orders of magnitude performance improvement while enabling online adversarial sample detection. |
| Tasks | |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02538v4 |
| http://arxiv.org/pdf/1709.02538v4.pdf | |
| PWC | https://paperswithcode.com/paper/deepfense-online-accelerated-defense-against |
| Repo | |
| Framework | |
Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection
| Title | Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection |
| Authors | Samaneh Nasiri Ghosheh Bolagh, Gari. D. Clifford |
| Abstract | Inter-subject variability between individuals poses a challenge in inter-subject brain signal analysis problems. A new algorithm for subject-selection based on clustering covariance matrices on a Riemannian manifold is proposed. After unsupervised selection of the subsets of relevant subjects, data in a cluster is mapped to a tangent space at the mean point of covariance matrices in that cluster and an SVM classifier on labeled data from relevant subjects is trained. Experiment on an EEG seizure database shows that the proposed method increases the accuracy over state-of-the-art from 86.83% to 89.84% and specificity from 87.38% to 89.64% while reducing the false positive rate/hour from 0.8/hour to 0.77/hour. |
| Tasks | EEG, Seizure Detection |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00465v1 |
| http://arxiv.org/pdf/1712.00465v1.pdf | |
| PWC | https://paperswithcode.com/paper/subject-selection-on-a-riemannian-manifold |
| Repo | |
| Framework | |
A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification
| Title | A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification |
| Authors | Yaoyuan Zhang, Zhenxu Ye, Yansong Feng, Dongyan Zhao, Rui Yan |
| Abstract | Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For sentence-level studies, sentences after simplification are fluent but sometimes are not really simplified. For word-level studies, words are simplified but also have potential grammar errors due to different usages of words before and after simplification. In this paper, we propose a two-step simplification framework by combining both the word-level and the sentence-level simplifications, making use of their corresponding advantages. Based on the two-step framework, we implement a novel constrained neural generation model to simplify sentences given simplified words. The final results on Wikipedia and Simple Wikipedia aligned datasets indicate that our method yields better performance than various baselines. |
| Tasks | |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02312v1 |
| http://arxiv.org/pdf/1704.02312v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-constrained-sequence-to-sequence-neural |
| Repo | |
| Framework | |
Visual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals
| Title | Visual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals |
| Authors | Sandipan Banerjee, James Sweet, Christopher Sweet, Marya Lieberman |
| Abstract | Falsification of medicines is a big problem in many developing countries, where technological infrastructure is inadequate to detect these harmful products. We have developed a set of inexpensive paper cards, called Paper Analytical Devices (PADs), which can efficiently classify drugs based on their chemical composition, as a potential solution to the problem. These cards have different reagents embedded in them which produce a set of distinctive color descriptors upon reacting with the chemical compounds that constitute pharmaceutical dosage forms. If a falsified version of the medicine lacks the active ingredient or includes substitute fillers, the difference in color is perceivable by humans. However, reading the cards with accuracy takes training and practice, which may hamper their scaling and implementation in low resource settings. To deal with this, we have developed an automatic visual recognition system to read the results from the PAD images. At first, the optimal set of reagents was found by running singular value decomposition on the intensity values of the color tones in the card images. A dataset of cards embedded with these reagents is produced to generate the most distinctive results for a set of 26 different active pharmaceutical ingredients (APIs) and excipients. Then, we train two popular convolutional neural network (CNN) models, with the card images. We also extract some “hand-crafted” features from the images and train a nearest neighbor classifier and a non-linear support vector machine with them. On testing, higher-level features performed much better in accurately classifying the PAD images, with the CNN models reaching the highest average accuracy of over 94%. |
| Tasks | |
| Published | 2017-04-13 |
| URL | http://arxiv.org/abs/1704.04251v1 |
| http://arxiv.org/pdf/1704.04251v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-recognition-of-paper-analytical-device |
| Repo | |
| Framework | |
Approximating the Backbone in the Weighted Maximum Satisfiability Problem
| Title | Approximating the Backbone in the Weighted Maximum Satisfiability Problem |
| Authors | He Jiang, Jifeng Xuan, Yan Hu |
| Abstract | The weighted Maximum Satisfiability problem (weighted MAX-SAT) is a NP-hard problem with numerous applications arising in artificial intelligence. As an efficient tool for heuristic design, the backbone has been applied to heuristics design for many NP-hard problems. In this paper, we investigated the computational complexity for retrieving the backbone in weighted MAX-SAT and developed a new algorithm for solving this problem. We showed that it is intractable to retrieve the full backbone under the assumption that . Moreover, it is intractable to retrieve a fixed fraction of the backbone as well. And then we presented a backbone guided local search (BGLS) with Walksat operator for weighted MAX-SAT. BGLS consists of two phases: the first phase samples the backbone information from local optima and the backbone phase conducts local search under the guideline of backbone. Extensive experimental results on the benchmark showed that BGLS outperforms the existing heuristics in both solution quality and runtime. |
| Tasks | |
| Published | 2017-04-16 |
| URL | http://arxiv.org/abs/1704.04775v1 |
| http://arxiv.org/pdf/1704.04775v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximating-the-backbone-in-the-weighted |
| Repo | |
| Framework | |
Semi-supervised Bayesian Deep Multi-modal Emotion Recognition
| Title | Semi-supervised Bayesian Deep Multi-modal Emotion Recognition |
| Authors | Changde Du, Changying Du, Jinpeng Li, Wei-long Zheng, Bao-liang Lu, Huiguang He |
| Abstract | In emotion recognition, it is difficult to recognize human’s emotional states using just a single modality. Besides, the annotation of physiological emotional data is particularly expensive. These two aspects make the building of effective emotion recognition model challenging. In this paper, we first build a multi-view deep generative model to simulate the generative process of multi-modality emotional data. By imposing a mixture of Gaussians assumption on the posterior approximation of the latent variables, our model can learn the shared deep representation from multiple modalities. To solve the labeled-data-scarcity problem, we further extend our multi-view model to semi-supervised learning scenario by casting the semi-supervised classification problem as a specialized missing data imputation task. Our semi-supervised multi-view deep generative framework can leverage both labeled and unlabeled data from multiple modalities, where the weight factor for each modality can be learned automatically. Compared with previous emotion recognition methods, our method is more robust and flexible. The experiments conducted on two real multi-modal emotion datasets have demonstrated the superiority of our framework over a number of competitors. |
| Tasks | Emotion Recognition, Imputation |
| Published | 2017-04-25 |
| URL | http://arxiv.org/abs/1704.07548v1 |
| http://arxiv.org/pdf/1704.07548v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-bayesian-deep-multi-modal |
| Repo | |
| Framework | |
Random Forests for Industrial Device Functioning Diagnostics Using Wireless Sensor Networks
| Title | Random Forests for Industrial Device Functioning Diagnostics Using Wireless Sensor Networks |
| Authors | Wiem Elghazel, Kamal Medjaher, Nourredine Zerhouni, Jacques Bahi, Ahamd Farhat, Christophe Guyeux, Mourad Hakem |
| Abstract | In this paper, random forests are proposed for operating devices diagnostics in the presence of a variable number of features. In various contexts, like large or difficult-to-access monitored areas, wired sensor networks providing features to achieve diagnostics are either very costly to use or totally impossible to spread out. Using a wireless sensor network can solve this problem, but this latter is more subjected to flaws. Furthermore, the networks’ topology often changes, leading to a variability in quality of coverage in the targeted area. Diagnostics at the sink level must take into consideration that both the number and the quality of the provided features are not constant, and that some politics like scheduling or data aggregation may be developed across the network. The aim of this article is ($1$) to show that random forests are relevant in this context, due to their flexibility and robustness, and ($2$) to provide first examples of use of this method for diagnostics based on data provided by a wireless sensor network. |
| Tasks | |
| Published | 2017-06-25 |
| URL | http://arxiv.org/abs/1706.08106v1 |
| http://arxiv.org/pdf/1706.08106v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-forests-for-industrial-device |
| Repo | |
| Framework | |
Transfer Learning by Asymmetric Image Weighting for Segmentation across Scanners
| Title | Transfer Learning by Asymmetric Image Weighting for Segmentation across Scanners |
| Authors | Veronika Cheplygina, Annegreet van Opbroek, M. Arfan Ikram, Meike W. Vernooij, Marleen de Bruijne |
| Abstract | Supervised learning has been very successful for automatic segmentation of images from a single scanner. However, several papers report deteriorated performances when using classifiers trained on images from one scanner to segment images from other scanners. We propose a transfer learning classifier that adapts to differences between training and test images. This method uses a weighted ensemble of classifiers trained on individual images. The weight of each classifier is determined by the similarity between its training image and the test image. We examine three unsupervised similarity measures, which can be used in scenarios where no labeled data from a newly introduced scanner or scanning protocol is available. The measures are based on a divergence, a bag distance, and on estimating the labels with a clustering procedure. These measures are asymmetric. We study whether the asymmetry can improve classification. Out of the three similarity measures, the bag similarity measure is the most robust across different studies and achieves excellent results on four brain tissue segmentation datasets and three white matter lesion segmentation datasets, acquired at different centers and with different scanners and scanning protocols. We show that the asymmetry can indeed be informative, and that computing the similarity from the test image to the training images is more appropriate than the opposite direction. |
| Tasks | Lesion Segmentation, Transfer Learning |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.04981v1 |
| http://arxiv.org/pdf/1703.04981v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-by-asymmetric-image |
| Repo | |
| Framework | |
Compatibility Family Learning for Item Recommendation and Generation
| Title | Compatibility Family Learning for Item Recommendation and Generation |
| Authors | Yong-Siang Shih, Kai-Yueh Chang, Hsuan-Tien Lin, Min Sun |
| Abstract | Compatibility between items, such as clothes and shoes, is a major factor among customer’s purchasing decisions. However, learning “compatibility” is challenging due to (1) broader notions of compatibility than those of similarity, (2) the asymmetric nature of compatibility, and (3) only a small set of compatible and incompatible items are observed. We propose an end-to-end trainable system to embed each item into a latent vector and project a query item into K compatible prototypes in the same space. These prototypes reflect the broad notions of compatibility. We refer to both the embedding and prototypes as “Compatibility Family”. In our learned space, we introduce a novel Projected Compatibility Distance (PCD) function which is differentiable and ensures diversity by aiming for at least one prototype to be close to a compatible item, whereas none of the prototypes are close to an incompatible item. We evaluate our system on a toy dataset, two Amazon product datasets, and Polyvore outfit dataset. Our method consistently achieves state-of-the-art performance. Finally, we show that we can visualize the candidate compatible prototypes using a Metric-regularized Conditional Generative Adversarial Network (MrCGAN), where the input is a projected prototype and the output is a generated image of a compatible item. We ask human evaluators to judge the relative compatibility between our generated images and images generated by CGANs conditioned directly on query items. Our generated images are significantly preferred, with roughly twice the number of votes as others. |
| Tasks | |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.01262v1 |
| http://arxiv.org/pdf/1712.01262v1.pdf | |
| PWC | https://paperswithcode.com/paper/compatibility-family-learning-for-item |
| Repo | |
| Framework | |
