Paper Group ANR 431
Elastic bands across the path: A new framework and methods to lower bound DTW. A review on distance based time series classification. MILE: A Multi-Level Framework for Scalable Graph Embedding. Improved Language Modeling by Decoding the Past. Learning to Multitask. Guidelines and Annotation Framework for Arabic Author Profiling. Learning Hash Codes …
Elastic bands across the path: A new framework and methods to lower bound DTW
| Title | Elastic bands across the path: A new framework and methods to lower bound DTW |
| Authors | Chang Wei Tan, Francois Petitjean, Geoffrey I. Webb |
| Abstract | There has been renewed recent interest in developing effective lower bounds for Dynamic Time Warping (DTW) distance between time series. These have many applications in time series indexing, clustering, forecasting, regression and classification. One of the key time series classification algorithms, the nearest neighbor algorithm with DTW distance (NN-DTW) is very expensive to compute, due to the quadratic complexity of DTW. Lower bound search can speed up NN-DTW substantially. An effective and tight lower bound quickly prunes off unpromising nearest neighbor candidates from the search space and minimises the number of the costly DTW computations. The speed up provided by lower bound search becomes increasingly critical as training set size increases. Different lower bounds provide different trade-offs between computation time and tightness. Most existing lower bounds interact with DTW warping window sizes. They are very tight and effective at smaller warping window sizes, but become looser as the warping window increases, thus reducing the pruning effectiveness for NN-DTW. In this work, we present a new class of lower bounds that are tighter than the popular Keogh lower bound, while requiring similar computation time. Our new lower bounds take advantage of the DTW boundary condition, monotonicity and continuity constraints to create a tighter lower bound. Of particular significance, they remain relatively tight even for large windows. A single parameter to these new lower bounds controls the speed-tightness trade-off. We demonstrate that these new lower bounds provide an exceptional balance between computation time and tightness for the NN-DTW time series classification task, resulting in greatly improved efficiency for NN-DTW lower bound search. |
| Tasks | Time Series, Time Series Classification |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.09617v3 |
| http://arxiv.org/pdf/1808.09617v3.pdf | |
| PWC | https://paperswithcode.com/paper/elastic-bands-across-the-path-a-new-framework |
| Repo | |
| Framework | |
A review on distance based time series classification
| Title | A review on distance based time series classification |
| Authors | Amaia Abanda, Usue Mori, Jose A. Lozano |
| Abstract | Time series classification is an increasing research topic due to the vast amount of time series data that are being created over a wide variety of fields. The particularity of the data makes it a challenging task and different approaches have been taken, including the distance based approach. 1-NN has been a widely used method within distance based time series classification due to it simplicity but still good performance. However, its supremacy may be attributed to being able to use specific distances for time series within the classification process and not to the classifier itself. With the aim of exploiting these distances within more complex classifiers, new approaches have arisen in the past few years that are competitive or which outperform the 1-NN based approaches. In some cases, these new methods use the distance measure to transform the series into feature vectors, bridging the gap between time series and traditional classifiers. In other cases, the distances are employed to obtain a time series kernel and enable the use of kernel methods for time series classification. One of the main challenges is that a kernel function must be positive semi-definite, a matter that is also addressed within this review. The presented review includes a taxonomy of all those methods that aim to classify time series using a distance based approach, as well as a discussion of the strengths and weaknesses of each method. |
| Tasks | Time Series, Time Series Classification |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04509v1 |
| http://arxiv.org/pdf/1806.04509v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-on-distance-based-time-series |
| Repo | |
| Framework | |
MILE: A Multi-Level Framework for Scalable Graph Embedding
| Title | MILE: A Multi-Level Framework for Scalable Graph Embedding |
| Authors | Jiongqian Liang, Saket Gurukar, Srinivasan Parthasarathy |
| Abstract | Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultI-Level Embedding (MILE) framework – a generic methodology allowing contemporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to maintain the backbone structure of the graph. It then applies existing embedding methods on the coarsest graph and refines the embeddings to the original graph through a novel graph convolution neural network that it learns. The proposed MILE framework is agnostic to the underlying graph embedding techniques and can be applied to many existing graph embedding methods without modifying them. We employ our framework on several popular graph embedding techniques and conduct embedding for real-world graphs. Experimental results on five large-scale datasets demonstrate that MILE significantly boosts the speed (order of magnitude) of graph embedding while also often generating embeddings of better quality for the task of node classification. MILE can comfortably scale to a graph with 9 million nodes and 40 million edges, on which existing methods run out of memory or take too long to compute on a modern workstation. |
| Tasks | Graph Embedding, Node Classification |
| Published | 2018-02-26 |
| URL | http://arxiv.org/abs/1802.09612v1 |
| http://arxiv.org/pdf/1802.09612v1.pdf | |
| PWC | https://paperswithcode.com/paper/mile-a-multi-level-framework-for-scalable |
| Repo | |
| Framework | |
Improved Language Modeling by Decoding the Past
| Title | Improved Language Modeling by Decoding the Past |
| Authors | Siddhartha Brahma |
| Abstract | Highly regularized LSTMs achieve impressive results on several benchmark datasets in language modeling. We propose a new regularization method based on decoding the last token in the context using the predicted distribution of the next token. This biases the model towards retaining more contextual information, in turn improving its ability to predict the next token. With negligible overhead in the number of parameters and training time, our Past Decode Regularization (PDR) method achieves a word level perplexity of 55.6 on the Penn Treebank and 63.5 on the WikiText-2 datasets using a single softmax. We also show gains by using PDR in combination with a mixture-of-softmaxes, achieving a word level perplexity of 53.8 and 60.5 on these datasets. In addition, our method achieves 1.169 bits-per-character on the Penn Treebank Character dataset for character level language modeling. These results constitute a new state-of-the-art in their respective settings. |
| Tasks | Language Modelling |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.05908v4 |
| http://arxiv.org/pdf/1808.05908v4.pdf | |
| PWC | https://paperswithcode.com/paper/improved-language-modeling-by-decoding-the |
| Repo | |
| Framework | |
Learning to Multitask
| Title | Learning to Multitask |
| Authors | Yu Zhang, Ying Wei, Qiang Yang |
| Abstract | Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called learning to multitask (L2MT). To achieve the goal, L2MT exploits historical multitask experience which is organized as a training set consists of several tuples, each of which contains a multitask problem with multiple tasks, a multitask model, and the relative test error. Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation. Given a new multitask problem, the estimation function is used to identify a suitable multitask model. Experiments on benchmark datasets show the effectiveness of the proposed L2MT framework. |
| Tasks | |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07541v1 |
| http://arxiv.org/pdf/1805.07541v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-multitask |
| Repo | |
| Framework | |
Guidelines and Annotation Framework for Arabic Author Profiling
| Title | Guidelines and Annotation Framework for Arabic Author Profiling |
| Authors | Wajdi Zaghouani, Anis Charfi |
| Abstract | In this paper, we present the annotation pipeline and the guidelines we wrote as part of an effort to create a large manually annotated Arabic author profiling dataset from various social media sources covering 16 Arabic countries and 11 dialectal regions. The target size of the annotated ARAP-Tweet corpus is more than 2.4 million words. We illustrate and summarize our general and dialect-specific guidelines for each of the dialectal regions selected. We also present the annotation framework and logistics. We control the annotation quality frequently by computing the inter-annotator agreement during the annotation process. Finally, we describe the issues encountered during the annotation phase, especially those related to the peculiarities of Arabic dialectal varieties as used in social media. |
| Tasks | |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07678v1 |
| http://arxiv.org/pdf/1808.07678v1.pdf | |
| PWC | https://paperswithcode.com/paper/guidelines-and-annotation-framework-for |
| Repo | |
| Framework | |
Learning Hash Codes via Hamming Distance Targets
| Title | Learning Hash Codes via Hamming Distance Targets |
| Authors | Martin Loncaric, Bowei Liu, Ryan Weber |
| Abstract | We present a powerful new loss function and training scheme for learning binary hash codes with any differentiable model and similarity function. Our loss function improves over prior methods by using log likelihood loss on top of an accurate approximation for the probability that two inputs fall within a Hamming distance target. Our novel training scheme obtains a good estimate of the true gradient by better sampling inputs and evaluating loss terms between all pairs of inputs in each minibatch. To fully leverage the resulting hashes, we use multi-indexing. We demonstrate that these techniques provide large improvements to a similarity search tasks. We report the best results to date on competitive information retrieval tasks for ImageNet and SIFT 1M, improving MAP from 73% to 84% and reducing query cost by a factor of 2-8, respectively. |
| Tasks | Information Retrieval |
| Published | 2018-10-01 |
| URL | http://arxiv.org/abs/1810.01008v1 |
| http://arxiv.org/pdf/1810.01008v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-hash-codes-via-hamming-distance |
| Repo | |
| Framework | |
Minimax Lower Bounds for Cost Sensitive Classification
| Title | Minimax Lower Bounds for Cost Sensitive Classification |
| Authors | Parameswaran Kamalaruban, Robert C. Williamson |
| Abstract | The cost-sensitive classification problem plays a crucial role in mission-critical machine learning applications, and differs with traditional classification by taking the misclassification costs into consideration. Although being studied extensively in the literature, the fundamental limits of this problem are still not well understood. We investigate the hardness of this problem by extending the standard minimax lower bound of balanced binary classification problem (due to \cite{massart2006risk}), and emphasize the impact of cost terms on the hardness. |
| Tasks | |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07723v1 |
| http://arxiv.org/pdf/1805.07723v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-lower-bounds-for-cost-sensitive |
| Repo | |
| Framework | |
Adversarial Gain
| Title | Adversarial Gain |
| Authors | Peter Henderson, Koustuv Sinha, Rosemary Nan Ke, Joelle Pineau |
| Abstract | Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily studied in the context of classification and computer vision tasks. While several attacks have been proposed in natural language processing (NLP) settings, they often vary in defining the parameters of an attack and what a successful attack would look like. The goal of this work is to propose a unifying model of adversarial examples suitable for NLP tasks in both generative and classification settings. We define the notion of adversarial gain: based in control theory, it is a measure of the change in the output of a system relative to the perturbation of the input (caused by the so-called adversary) presented to the learner. This definition, as we show, can be used under different feature spaces and distance conditions to determine attack or defense effectiveness across different intuitive manifolds. This notion of adversarial gain not only provides a useful way for evaluating adversaries and defenses, but can act as a building block for future work in robustness under adversaries due to its rooted nature in stability and manifold theory. |
| Tasks | |
| Published | 2018-11-04 |
| URL | http://arxiv.org/abs/1811.01302v1 |
| http://arxiv.org/pdf/1811.01302v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-gain |
| Repo | |
| Framework | |
The AAU Multimodal Annotation Toolboxes: Annotating Objects in Images and Videos
| Title | The AAU Multimodal Annotation Toolboxes: Annotating Objects in Images and Videos |
| Authors | Chris H. Bahnsen, Andreas Møgelmose, Thomas B. Moeslund |
| Abstract | This tech report gives an introduction to two annotation toolboxes that enable the creation of pixel and polygon-based masks as well as bounding boxes around objects of interest. Both toolboxes support the annotation of sequential images in the RGB and thermal modalities. Each annotated object is assigned a classification tag, a unique ID, and one or more optional meta data tags. The toolboxes are written in C++ with the OpenCV and Qt libraries and are operated by using the visual interface and the extensive range of keyboard shortcuts. Pre-built binaries are available for Windows and MacOS and the tools can be built from source under Linux as well. So far, tens of thousands of frames have been annotated using the toolboxes. |
| Tasks | |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03171v1 |
| http://arxiv.org/pdf/1809.03171v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-aau-multimodal-annotation-toolboxes |
| Repo | |
| Framework | |
Symmetry constrained machine learning
| Title | Symmetry constrained machine learning |
| Authors | Doron L. Bergman |
| Abstract | Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively in machine learning, until rather recently. In this article we show a general way to incorporate symmetries into machine learning models. We demonstrate this with a detailed analysis on a rather simple real world machine learning system - a neural network for classifying handwritten digits, lacking bias terms for every neuron. We demonstrate that ignoring symmetries can have dire over-fitting consequences, and that incorporating symmetry into the model reduces over-fitting, while at the same time reducing complexity, ultimately requiring less training data, and taking less time and resources to train. |
| Tasks | |
| Published | 2018-11-16 |
| URL | https://arxiv.org/abs/1811.07051v2 |
| https://arxiv.org/pdf/1811.07051v2.pdf | |
| PWC | https://paperswithcode.com/paper/symmetry-constrained-machine-learning |
| Repo | |
| Framework | |
A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities
| Title | A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities |
| Authors | Bo Zhou, Yuemeng Li, Jiangcong Wang |
| Abstract | We present a weakly supervised deep learning model for classifying thoracic diseases and identifying abnormalities in chest radiography. In this work, instead of learning from medical imaging data with region-level annotations, our model was merely trained on imaging data with image-level labels to classify diseases, and is able to identify abnormal image regions simultaneously. Our model consists of a customized pooling structure and an adaptive DenseNet front-end, which can effectively recognize possible disease features for classification and localization tasks. Our method has been validated on the publicly available ChestX-ray14 dataset. Experimental results have demonstrated that our classification and localization prediction performance achieved significant improvement over the previous models on the ChestX-ray14 dataset. In summary, our network can produce accurate disease classification and localization, which can potentially support clinical decisions. |
| Tasks | |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01257v2 |
| http://arxiv.org/pdf/1807.01257v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-weakly-supervised-adaptive-densenet-for |
| Repo | |
| Framework | |
Machine Learning-based Variability Handling in IoT Agents
| Title | Machine Learning-based Variability Handling in IoT Agents |
| Authors | Nathalia Nascimento, Paulo Alencar, Carlos Lucena, Donald Cowan |
| Abstract | Agent-based IoT applications have recently been proposed in several domains, such as health care, smart cities and agriculture. Deploying these applications in specific settings has been very challenging for many reasons including the complex static and dynamic variability of the physical devices such as sensors and actuators, the software application behavior and the environment in which the application is embedded. In this paper, we propose a self-configurable IoT agent approach based on feedback-evaluative machine-learning. The approach involves: i) a variability model of IoT agents; ii) generation of sets of customized agents; iii) feedback evaluative machine learning; iv) modeling and composition of a group of IoT agents; and v) a feature-selection method based on manual and automatic feedback. |
| Tasks | Feature Selection |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.03858v1 |
| http://arxiv.org/pdf/1802.03858v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-based-variability-handling |
| Repo | |
| Framework | |
Embedding a $θ$-invariant code into a complete one
| Title | Embedding a $θ$-invariant code into a complete one |
| Authors | Jean Néraud, Carla Selmi |
| Abstract | Let A be a finite or countable alphabet and let $\theta$ be a literal (anti-)automorphism onto A * (by definition, such a correspondence is determinated by a permutation of the alphabet). This paper deals with sets which are invariant under $\theta$ ($\theta$-invariant for short) that is, languages L such that $\theta$ (L) is a subset of L.We establish an extension of the famous defect theorem. With regards to the so-called notion of completeness, we provide a series of examples of finite complete $\theta$-invariant codes. Moreover, we establish a formula which allows to embed any non-complete $\theta$-invariant code into a complete one. As a consequence, in the family of the so-called thin $\theta$–invariant codes, maximality and completeness are two equivalent notions. |
| Tasks | |
| Published | 2018-01-16 |
| URL | http://arxiv.org/abs/1801.05164v3 |
| http://arxiv.org/pdf/1801.05164v3.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-a-invariant-code-into-a-complete |
| Repo | |
| Framework | |
Reusing Neural Speech Representations for Auditory Emotion Recognition
| Title | Reusing Neural Speech Representations for Auditory Emotion Recognition |
| Authors | Egor Lakomkin, Cornelius Weber, Sven Magg, Stefan Wermter |
| Abstract | Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion perception resulting in low annotator agreement, and the uncertainty about which features are the most relevant and robust ones for classification. In this paper, we will tackle the latter problem. Inspired by the recent success of transfer learning methods we propose a set of architectures which utilize neural representations inferred by training on large speech databases for the acoustic emotion recognition task. Our experiments on the IEMOCAP dataset show ~10% relative improvements in the accuracy and F1-score over the baseline recurrent neural network which is trained end-to-end for emotion recognition. |
| Tasks | Emotion Recognition, Transfer Learning |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11508v1 |
| http://arxiv.org/pdf/1803.11508v1.pdf | |
| PWC | https://paperswithcode.com/paper/reusing-neural-speech-representations-for |
| Repo | |
| Framework | |
