Paper Group ANR 777
Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets. Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network. Reinforcement Learning with Fairness Constraints for Resource Distribution in Human-Robot Teams. Approximate Dynamic Programming For Linear Systems with …
Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets
| Title | Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets |
| Authors | Mehrdad Ghadiri, Mark Schmidt |
| Abstract | There are many problems in machine learning and data mining which are equivalent to selecting a non-redundant, high “quality” set of objects. Recommender systems, feature selection, and data summarization are among many applications of this. In this paper, we consider this problem as an optimization problem that seeks to maximize the sum of a sum-sum diversity function and a non-negative monotone submodular function. The diversity function addresses the redundancy, and the submodular function controls the predictive quality. We consider the problem in big data settings (in other words, distributed and streaming settings) where the data cannot be stored on a single machine or the process time is too high for a single machine. We show that a greedy algorithm achieves a constant factor approximation of the optimal solution in these settings. Moreover, we formulate the multi-label feature selection problem as such an optimization problem. This formulation combined with our algorithm leads to the first distributed multi-label feature selection method. We compare the performance of this method with centralized multi-label feature selection methods in the literature, and we show that its performance is comparable or in some cases is even better than current centralized multi-label feature selection methods. |
| Tasks | Data Summarization, Feature Selection, Recommendation Systems |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08351v2 |
| http://arxiv.org/pdf/1903.08351v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-maximization-of-submodular-plus |
| Repo | |
| Framework | |
Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network
| Title | Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network |
| Authors | Mustafa Talha Avcu, Zhuo Zhang, Derrick Wei Shih Chan |
| Abstract | This work aims to develop an end-to-end solution for seizure onset detection. We design the SeizNet, a Convolutional Neural Network for seizure detection. To compare SeizNet with traditional machine learning approach, a baseline classifier is implemented using spectrum band power features with Support Vector Machines (BPsvm). We explore the possibility to use the least number of channels for accurate seizure detection by evaluating SeizNet and BPsvm approaches using all channels and two channels settings respectively. EEG Data is acquired from 29 pediatric patients admitted to KK Woman’s and Children’s Hospital who were diagnosed as typical absence seizures. We conduct leave-one-out cross validation for all subjects. Using full channel data, BPsvm yields a sensitivity of 86.6% and 0.84 false alarm (per hour) while SeizNet yields overall sensitivity of 95.8 % with 0.17 false alarm. More interestingly, two channels seizNet outperforms full channel BPsvm with a sensitivity of 93.3% and 0.58 false alarm. We further investigate interpretability of SeizNet by decoding the filters learned along convolutional layers. Seizure-like characteristics can be clearly observed in the filters from third and forth convolutional layers. |
| Tasks | EEG, Seizure Detection |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.05305v1 |
| http://arxiv.org/pdf/1901.05305v1.pdf | |
| PWC | https://paperswithcode.com/paper/seizure-detection-using-least-eeg-channels-by |
| Repo | |
| Framework | |
Reinforcement Learning with Fairness Constraints for Resource Distribution in Human-Robot Teams
| Title | Reinforcement Learning with Fairness Constraints for Resource Distribution in Human-Robot Teams |
| Authors | Houston Claure, Yifang Chen, Jignesh Modi, Malte Jung, Stefanos Nikolaidis |
| Abstract | Much work in robotics and operations research has focused on optimal resource distribution, where an agent dynamically decides how to sequentially distribute resources among different candidates. However, most work ignores the notion of fairness in candidate selection. In the case where a robot distributes resources to human team members, disproportionately favoring the highest performing teammate can have negative effects in team dynamics and system acceptance. We introduce a multi-armed bandit algorithm with fairness constraints, where a robot distributes resources to human teammates of different skill levels. In this problem, the robot does not know the skill level of each human teammate, but learns it by observing their performance over time. We define fairness as a constraint on the minimum rate that each human teammate is selected throughout the task. We provide theoretical guarantees on performance and perform a large-scale user study, where we adjust the level of fairness in our algorithm. Results show that fairness in resource distribution has a significant effect on users’ trust in the system. |
| Tasks | |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00313v2 |
| https://arxiv.org/pdf/1907.00313v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-fairness |
| Repo | |
| Framework | |
Approximate Dynamic Programming For Linear Systems with State and Input Constraints
| Title | Approximate Dynamic Programming For Linear Systems with State and Input Constraints |
| Authors | Ankush Chakrabarty, Rien Quirynen, Claus Danielson, Weinan Gao |
| Abstract | Enforcing state and input constraints during reinforcement learning (RL) in continuous state spaces is an open but crucial problem which remains a roadblock to using RL in safety-critical applications. This paper leverages invariant sets to update control policies within an approximate dynamic programming (ADP) framework that guarantees constraint satisfaction for all time and converges to the optimal policy (in a linear quadratic regulator sense) asymptotically. An algorithm for implementing the proposed constrained ADP approach in a data-driven manner is provided. The potential of this formalism is demonstrated via numerical examples. |
| Tasks | |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.11369v1 |
| https://arxiv.org/pdf/1906.11369v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-dynamic-programming-for-linear |
| Repo | |
| Framework | |
End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets
| Title | End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets |
| Authors | Ahmed Imtiaz Humayun, Asif Shahriyar Sushmit, Taufiq Hasan, Mohammed Imamul Hassan Bhuiyan |
| Abstract | Humans approximately spend a third of their life sleeping, which makes monitoring sleep an integral part of well-being. In this paper, a 34-layer deep residual ConvNet architecture for end-to-end sleep staging is proposed. The network takes raw single channel electroencephalogram (Fpz-Cz) signal as input and yields hypnogram annotations for each 30s segments as output. Experiments are carried out for two different scoring standards (5 and 6 stage classification) on the expanded PhysioNet Sleep-EDF dataset, which contains multi-source data from hospital and household polysomnography setups. The performance of the proposed network is compared with that of the state-of-the-art algorithms in patient independent validation tasks. The experimental results demonstrate the superiority of the proposed network compared to the best existing method, providing a relative improvement in epoch-wise average accuracy of 6.8% and 6.3% on the household data and multi-source data, respectively. Codes are made publicly available on Github. |
| Tasks | EEG |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10255v1 |
| http://arxiv.org/pdf/1904.10255v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-sleep-staging-with-raw-single |
| Repo | |
| Framework | |
Zero-shot Learning via Simultaneous Generating and Learning
| Title | Zero-shot Learning via Simultaneous Generating and Learning |
| Authors | Hyeonwoo Yu, Beomhee Lee |
| Abstract | To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting relations between classes of seen and unseen, we present a deep generative model to provide the model with experience about both seen and unseen classes. Based on the variational auto-encoder with class-specific multi-modal prior, the proposed method learns the conditional distribution of seen and unseen classes. In order to circumvent the need for samples of unseen classes, we treat the non-existing data as missing examples. That is, our network aims to find optimal unseen datapoints and model parameters, by iteratively following the generating and learning strategy. Since we obtain the conditional generative model for both seen and unseen classes, classification as well as generation can be performed directly without any off-the-shell classifiers. In experimental results, we demonstrate that the proposed generating and learning strategy makes the model achieve the outperforming results compared to that trained only on the seen classes, and also to the several state-of-the-art methods. |
| Tasks | Zero-Shot Learning |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09446v1 |
| https://arxiv.org/pdf/1910.09446v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-learning-via-simultaneous |
| Repo | |
| Framework | |
Hermitian matrices for clustering directed graphs: insights and applications
| Title | Hermitian matrices for clustering directed graphs: insights and applications |
| Authors | Mihai Cucuringu, Huan Li, He Sun, Luca Zanetti |
| Abstract | Graph clustering is a basic technique in machine learning, and has widespread applications in different domains. While spectral techniques have been successfully applied for clustering undirected graphs, the performance of spectral clustering algorithms for directed graphs (digraphs) is not in general satisfactory: these algorithms usually require symmetrising the matrix representing a digraph, and typical objective functions for undirected graph clustering do not capture cluster-structures in which the information given by the direction of the edges is crucial. To overcome these downsides, we propose a spectral clustering algorithm based on a complex-valued matrix representation of digraphs. We analyse its theoretical performance on a Stochastic Block Model for digraphs in which the cluster-structure is given not only by variations in edge densities, but also by the direction of the edges. The significance of our work is highlighted on a data set pertaining to internal migration in the United States: while previous spectral clustering algorithms for digraphs can only reveal that people are more likely to move between counties that are geographically close, our approach is able to cluster together counties with a similar socio-economical profile even when they are geographically distant, and illustrates how people tend to move from rural to more urbanised areas. |
| Tasks | Graph Clustering |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02096v1 |
| https://arxiv.org/pdf/1908.02096v1.pdf | |
| PWC | https://paperswithcode.com/paper/hermitian-matrices-for-clustering-directed |
| Repo | |
| Framework | |
Mixing of Stochastic Accelerated Gradient Descent
| Title | Mixing of Stochastic Accelerated Gradient Descent |
| Authors | Peiyuan Zhang, Hadi Daneshmand, Thomas Hofmann |
| Abstract | We study the mixing properties for stochastic accelerated gradient descent (SAGD) on least-squares regression. First, we show that stochastic gradient descent (SGD) and SAGD are simulating the same invariant distribution. Motivated by this, we then establish mixing rate for SAGD-iterates and compare it with those of SGD-iterates. Theoretically, we prove that the chain of SAGD iterates is geometrically ergodic –using a proper choice of parameters and under regularity assumptions on the input distribution. More specifically, we derive an explicit mixing rate depending on the first 4 moments of the data distribution. By means of illustrative examples, we prove that SAGD-iterate chain mixes faster than the chain of iterates obtained by SGD. Furthermore, we highlight applications of the established mixing rate in the convergence analysis of SAGD on realizable objectives. The proposed analysis is based on a novel non-asymptotic analysis of products of random matrices. This theoretical result is substantiated and validated by experiments. |
| Tasks | Stochastic Optimization |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14616v1 |
| https://arxiv.org/pdf/1910.14616v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixing-of-stochastic-accelerated-gradient |
| Repo | |
| Framework | |
Statistical guarantees for local graph clustering
| Title | Statistical guarantees for local graph clustering |
| Authors | Wooseok Ha, Kimon Fountoulakis, Michael W. Mahoney |
| Abstract | Local graph clustering methods aim to find small clusters in very large graphs. These methods take as input a graph and a seed node, and they return as output a good cluster in a running time that depends on the size of the output cluster but that is independent of the size of the input graph. In this paper, we adopt a statistical perspective on local graph clustering, and we analyze the performance of the l1-regularized PageRank method~(Fountoulakis et. al.) for the recovery of a single target cluster, given a seed node inside the cluster. Assuming the target cluster has been generated by a random model, we present two results. In the first, we show that the optimal support of l1-regularized PageRank recovers the full target cluster, with bounded false positives. In the second, we show that if the seed node is connected solely to the target cluster then the optimal support of l1-regularized PageRank recovers exactly the target cluster. We also show empirically that l1-regularized PageRank has a state-of-the-art performance on many real graphs, demonstrating the superiority of the method. From a computational perspective, we show that the solution path of l1-regularized PageRank is monotonic. This allows for the application of the forward stagewise algorithm, which approximates the solution path in running time that does not depend on the size of the whole graph. Finally, we show that l1-regularized PageRank and approximate personalized PageRank (APPR), another very popular method for local graph clustering, are equivalent in the sense that we can lower and upper bound the output of one with the output of the other. Based on this relation, we establish for APPR similar results to those we establish for l1-regularized PageRank. |
| Tasks | Graph Clustering |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04863v3 |
| https://arxiv.org/pdf/1906.04863v3.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-guarantees-for-local-graph |
| Repo | |
| Framework | |
CalBehav: A Machine Learning based Personalized Calendar Behavioral Model using Time-Series Smartphone Data
| Title | CalBehav: A Machine Learning based Personalized Calendar Behavioral Model using Time-Series Smartphone Data |
| Authors | Iqbal H. Sarker, Alan Colman, Jun Han, A. S. M. Kayes, Paul Watters |
| Abstract | The electronic calendar is a valuable resource nowadays for managing our daily life appointments or schedules, also known as events, ranging from professional to highly personal. Researchers have studied various types of calendar events to predict smartphone user behavior for incoming mobile communications. However, these studies typically do not take into account behavioral variations between individuals. In the real world, smartphone users can differ widely from each other in how they respond to incoming communications during their scheduled events. Moreover, an individual user may respond the incoming communications differently in different contexts subject to what type of event is scheduled in her personal calendar. Thus, a static calendar-based behavioral model for individual smartphone users does not necessarily reflect their behavior to the incoming communications. In this paper, we present a machine learning based context-aware model that is personalized and dynamically identifies individual’s dominant behavior for their scheduled events using logged time-series smartphone data, and shortly name as ``CalBehav’'. The experimental results based on real datasets from calendar and phone logs, show that this data-driven personalized model is more effective for intelligently managing the incoming mobile communications compared to existing calendar-based approaches. | |
| Tasks | Time Series |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.04724v1 |
| https://arxiv.org/pdf/1909.04724v1.pdf | |
| PWC | https://paperswithcode.com/paper/calbehav-a-machine-learning-based |
| Repo | |
| Framework | |
Detecting Syntactic Change Using a Neural Part-of-Speech Tagger
| Title | Detecting Syntactic Change Using a Neural Part-of-Speech Tagger |
| Authors | William Merrill, Gigi Felice Stark, Robert Frank |
| Abstract | We train a diachronic long short-term memory (LSTM) part-of-speech tagger on a large corpus of American English from the 19th, 20th, and 21st centuries. We analyze the tagger’s ability to implicitly learn temporal structure between years, and the extent to which this knowledge can be transferred to date new sentences. The learned year embeddings show a strong linear correlation between their first principal component and time. We show that temporal information encoded in the model can be used to predict novel sentences’ years of composition relatively well. Comparisons to a feedforward baseline suggest that the temporal change learned by the LSTM is syntactic rather than purely lexical. Thus, our results suggest that our tagger is implicitly learning to model syntactic change in American English over the course of the 19th, 20th, and early 21st centuries. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01661v2 |
| https://arxiv.org/pdf/1906.01661v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-syntactic-change-using-a-neural |
| Repo | |
| Framework | |
Bonn Activity Maps: Dataset Description
| Title | Bonn Activity Maps: Dataset Description |
| Authors | Julian Tanke, Oh-Hun Kwon, Patrick Stotko, Radu Alexandru Rosu, Michael Weinmann, Hassan Errami, Sven Behnke, Maren Bennewitz, Reinhard Klein, Andreas Weber, Angela Yao, Juergen Gall |
| Abstract | The key prerequisite for accessing the huge potential of current machine learning techniques is the availability of large databases that capture the complex relations of interest. Previous datasets are focused on either 3D scene representations with semantic information, tracking of multiple persons and recognition of their actions, or activity recognition of a single person in captured 3D environments. We present Bonn Activity Maps, a large-scale dataset for human tracking, activity recognition and anticipation of multiple persons. Our dataset comprises four different scenes that have been recorded by time-synchronized cameras each only capturing the scene partially, the reconstructed 3D models with semantic annotations, motion trajectories for individual people including 3D human poses as well as human activity annotations. We utilize the annotations to generate activity likelihoods on the 3D models called activity maps. |
| Tasks | Activity Recognition |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06354v1 |
| https://arxiv.org/pdf/1912.06354v1.pdf | |
| PWC | https://paperswithcode.com/paper/bonn-activity-maps-dataset-description |
| Repo | |
| Framework | |
Clustering-aware Graph Construction: A Joint Learning Perspective
| Title | Clustering-aware Graph Construction: A Joint Learning Perspective |
| Authors | Yuheng Jia, Hui Liu, Junhui Hou, Sam Kwong |
| Abstract | Graph-based clustering methods have demonstrated the effectiveness in various applications. Generally, existing graph-based clustering methods first construct a graph to represent the input data and then partition it to generate the clustering result. However, such a stepwise manner may make the constructed graph not fit the requirements for the subsequent decomposition, leading to compromised clustering accuracy. To this end, we propose a joint learning framework, which is able to learn the graph and the clustering result simultaneously, such that the resulting graph is tailored to the clustering task. The proposed model is formulated as a well-defined nonnegative and off-diagonal constrained optimization problem, which is further efficiently solved with convergence theoretically guaranteed. The advantage of the proposed model is demonstrated by comparing with 19 state-of-the-art clustering methods on 10 datasets with 4 clustering metrics. |
| Tasks | Graph Clustering, graph construction |
| Published | 2019-05-04 |
| URL | https://arxiv.org/abs/1905.01446v3 |
| https://arxiv.org/pdf/1905.01446v3.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-aware-graph-construction-a-joint |
| Repo | |
| Framework | |
An application of a deep learning algorithm for automatic detection of unexpected accidents under bad CCTV monitoring conditions in tunnels
| Title | An application of a deep learning algorithm for automatic detection of unexpected accidents under bad CCTV monitoring conditions in tunnels |
| Authors | Kyu-Beom Lee, Hyu-Soung Shin |
| Abstract | In this paper, Object Detection and Tracking System (ODTS) in combination with a well-known deep learning network, Faster Regional Convolution Neural Network (Faster R-CNN), for Object Detection and Conventional Object Tracking algorithm will be introduced and applied for automatic detection and monitoring of unexpected events on CCTVs in tunnels, which are likely to (1) Wrong-Way Driving (WWD), (2) Stop, (3) Person out of vehicle in tunnel (4) Fire. ODTS accepts a video frame in time as an input to obtain Bounding Box (BBox) results by Object Detection and compares the BBoxs of the current and previous video frames to assign a unique ID number to each moving and detected object. This system makes it possible to track a moving object in time, which is not usual to be achieved in conventional object detection frameworks. A deep learning model in ODTS was trained with a dataset of event images in tunnels to Average Precision (AP) values of 0.8479, 0.7161 and 0.9085 for target objects: Car, Person, and Fire, respectively. Then, based on trained deep learning model, the ODTS based Tunnel CCTV Accident Detection System was tested using four accident videos which including each accident. As a result, the system can detect all accidents within 10 seconds. The more important point is that the detection capacity of ODTS could be enhanced automatically without any changes in the program codes as the training dataset becomes rich. |
| Tasks | Object Detection, Object Tracking |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.11094v1 |
| https://arxiv.org/pdf/1910.11094v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-application-of-a-deep-learning-algorithm |
| Repo | |
| Framework | |
Emotion Detection and Analysis on Social Media
| Title | Emotion Detection and Analysis on Social Media |
| Authors | Bharat Gaind, Varun Syal, Sneha Padgalwar |
| Abstract | In this paper, we address the problem of detection, classification and quantification of emotions of text in any form. We consider English text collected from social media like Twitter, which can provide information having utility in a variety of ways, especially opinion mining. Social media like Twitter and Facebook is full of emotions, feelings and opinions of people all over the world. However, analyzing and classifying text on the basis of emotions is a big challenge and can be considered as an advanced form of Sentiment Analysis. This paper proposes a method to classify text into six different Emotion-Categories: Happiness, Sadness, Fear, Anger, Surprise and Disgust. In our model, we use two different approaches and combine them to effectively extract these emotions from text. The first approach is based on Natural Language Processing, and uses several textual features like emoticons, degree words and negations, Parts Of Speech and other grammatical analysis. The second approach is based on Machine Learning classification algorithms. We have also successfully devised a method to automate the creation of the training-set itself, so as to eliminate the need of manual annotation of large datasets. Moreover, we have managed to create a large bag of emotional words, along with their emotion-intensities. On testing, it is shown that our model provides significant accuracy in classifying tweets taken from Twitter. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08458v2 |
| https://arxiv.org/pdf/1901.08458v2.pdf | |
| PWC | https://paperswithcode.com/paper/emotion-detection-and-analysis-on-social |
| Repo | |
| Framework | |
