Paper Group NAWR 30
Restructuring Endpoint Congestion Control. Jack the Reader – A Machine Reading Framework. Few-Shot Learning with Graph Neural Networks. Monotonic Chunkwise Attention. Where is my URI?. Generative Domain-Migration Hashing for Sketch-to-Image Retrieval. A Scalable Laplace Approximation for Neural Networks. Towards understanding ECG rhythm classifica …
Restructuring Endpoint Congestion Control
Title | Restructuring Endpoint Congestion Control |
Authors | Akshay Narayan, Frank Cangialosi, Deepti Raghavan, Prateesh Goyal Srinivas Narayana, Radhika Mittal, Mohammad Alizadeh, Hari Balakrishnan |
Abstract | Overview: CCP provides a simple and convenient programming interface for writing real, scalable implementations of congestion control algorithms in user-space, so you can focus purely on the algorithmic details and not battle the Linux kernel. Write algorithms in Rust or Python rather than C, without having to ever recompile the kernel and without worrying about crashing the kernel. Your algorithm also instantly runs on any other datapath we support (Google QUIC and mTCP-on-DPDK at the moment). If you implement a new algorithm on CCP, please let us know and we will add your project to a list of new algorithms we maintain. Abstract: This paper describes the implementation and evaluation of a system to implement complex congestion control functions by placing them in a separate agent outside the datapath. Each datapath—such as the Linux kernel TCP, UDP-based QUIC, or kernel-bypass transports like mTCP-on-DPDK—summarizes information about packet round-trip times, receptions, losses, and ECN via a well-defined interface to algorithms running in the off-datapath Congestion Control Plane (CCP). The algorithms use this information to control the datapath’s congestion window or pacing rate. Algorithms written in CCP can run on multiple datapaths. CCP improves both the pace of development and ease of maintenance of congestion control algorithms by providing better, modular abstractions, and supports aggregation capabilities of the Congestion Manager, all with one-time changes to datapaths. CCP also enables new capabilities, such as Copa in Linux TCP, several algorithms running on QUIC and mTCP/DPDK, and the use of signal processing algorithms to detect whether cross-traffic is ACK-clocked. Experiments with our user-level Linux CCP implementation show that CCP algorithms behave similarly to kernel algorithms, and incur modest CPU overhead of a few percent. |
Tasks | |
Published | 2018-08-20 |
URL | https://people.csail.mit.edu/frankc/ |
https://people.csail.mit.edu/frankc/pubs/ccp-sigcomm18.pdf | |
PWC | https://paperswithcode.com/paper/restructuring-endpoint-congestion-control |
Repo | https://github.com/ccp-project/portus |
Framework | none |
Jack the Reader – A Machine Reading Framework
Title | Jack the Reader – A Machine Reading Framework |
Authors | Dirk Weissenborn, Pasquale Minervini, Isabelle Augenstein, Johannes Welbl, Tim Rockt{"a}schel, Matko Bo{\v{s}}njak, Jeff Mitchell, Thomas Demeester, Tim Dettmers, Pontus Stenetorp, Sebastian Riedel |
Abstract | Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as questions. Providing a set of useful primitives operating in a single framework of related tasks would allow for expressive modelling, and easier model comparison and replication. To that end, we present Jack the Reader (JACK), a framework for Machine Reading that allows for quick model prototyping by component reuse, evaluation of new models on existing datasets as well as integrating new datasets and applying them on a growing set of implemented baseline models. JACK is currently supporting (but not limited to) three tasks: Question Answering, Natural Language Inference, and Link Prediction. It is developed with the aim of increasing research efficiency and code reuse. |
Tasks | Information Retrieval, Link Prediction, Natural Language Inference, Question Answering, Reading Comprehension |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-4005/ |
https://www.aclweb.org/anthology/P18-4005 | |
PWC | https://paperswithcode.com/paper/jack-the-reader-a-a-machine-reading-framework |
Repo | https://github.com/uclmr/jack |
Framework | tf |
Few-Shot Learning with Graph Neural Networks
Title | Few-Shot Learning with Graph Neural Networks |
Authors | Victor Garcia Satorras, Joan Bruna Estrach |
Abstract | We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot learning models. Besides providing improved numerical performance, our framework is easily extended to variants of few-shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based models to operate well on ‘relational’ tasks. |
Tasks | Active Learning, Few-Shot Learning |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=BJj6qGbRW |
https://openreview.net/pdf?id=BJj6qGbRW | |
PWC | https://paperswithcode.com/paper/few-shot-learning-with-graph-neural-networks-1 |
Repo | https://github.com/vgsatorras/few-shot-gnn |
Framework | pytorch |
Monotonic Chunkwise Attention
Title | Monotonic Chunkwise Attention |
Authors | Chung-Cheng Chiu*, Colin Raffel* |
Abstract | Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptively splits the input sequence into small chunks over which soft attention is computed. We show that models utilizing MoChA can be trained efficiently with standard backpropagation while allowing online and linear-time decoding at test time. When applied to online speech recognition, we obtain state-of-the-art results and match the performance of a model using an offline soft attention mechanism. In document summarization experiments where we do not expect monotonic alignments, we show significantly improved performance compared to a baseline monotonic attention-based model. |
Tasks | Document Summarization, Speech Recognition |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=Hko85plCW |
https://openreview.net/pdf?id=Hko85plCW | |
PWC | https://paperswithcode.com/paper/monotonic-chunkwise-attention-1 |
Repo | https://github.com/craffel/mocha |
Framework | tf |
Where is my URI?
Title | Where is my URI? |
Authors | Andre Valdestilhas, Tommaso Soru, Markus Nentwig, Edgard Marx, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo |
Abstract | One of the Semantic Web foundations is the possibility to dereference URIs to let applications negotiate their semantic content. However, this exploitation is often infeasible as the availability of such information depends on the reliability of networks, services, and human factors. Moreover, it has been shown that around 90% of the information published as Linked Open Data is available as data dumps and more than 60% of endpoints are offline. To this end, we propose a Web service called Where is my URI?. Our service aims at indexing URIs and their use in order to let Linked Data consumers find the respective RDF data source, in case such information cannot be retrieved from the URI alone. We rank the corresponding datasets by following the rationale upon which a dataset contributes to the definition of a URI proportionally to the number of literals. We finally describe potential use-cases of applications that can immediately benefit from our simple yet useful service. |
Tasks | RDF Dataset Discovery |
Published | 2018-06-15 |
URL | https://www.researchgate.net/publication/325529570_Where_is_My_URI |
https://svn.aksw.org/papers/2018/ESWC_WIMU/public.pdf | |
PWC | https://paperswithcode.com/paper/where-is-my-uri |
Repo | https://github.com/dice-group/wimu |
Framework | none |
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
Title | Generative Domain-Migration Hashing for Sketch-to-Image Retrieval |
Authors | Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc Van Gool |
Abstract | Due to the succinct nature of free-hand sketch drawings, sketch-based image retrieval (SBIR) has abundant practical use cases in consumer electronics. However, SBIR remains a long-standing unsolved problem mainly due to the significant discrepancy between the sketch domain and the image domain. In this work, we propose a Generative Domain-migration Hashing (GDH) approach, which for the first time generates hashing codes from synthetic natural images that are migrated from sketches. The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability. With the robust mapping learned from the generative model, GDH can migrate sketches to their indistinguishable image counterparts while preserving the domain-invariant information of sketches. With an end-to-end multi-task learning framework, the generative model and binarized hashing codes can be jointly optimized. Comprehensive experiments of both category-level and fine-grained SBIR on multiple large-scale datasets demonstrate the consistently balanced superiority of GDH in terms of efficiency, memory costs and effectiveness. |
Tasks | Image Retrieval, Multi-Task Learning, Sketch-Based Image Retrieval |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jingyi_Zhang_Generative_Domain-Migration_Hashing_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Jingyi_Zhang_Generative_Domain-Migration_Hashing_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/generative-domain-migration-hashing-for |
Repo | https://github.com/YCJGG/GDH |
Framework | pytorch |
A Scalable Laplace Approximation for Neural Networks
Title | A Scalable Laplace Approximation for Neural Networks |
Authors | Hippolyt Ritter, Aleksandar Botev, David Barber |
Abstract | Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more |
Tasks | Bayesian Inference |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=Skdvd2xAZ |
https://openreview.net/pdf?id=Skdvd2xAZ | |
PWC | https://paperswithcode.com/paper/a-scalable-laplace-approximation-for-neural |
Repo | https://github.com/JavierAntoran/Bayesian-Neural-Networks |
Framework | pytorch |
Towards understanding ECG rhythm classification using convolutional neural networks and attention mappings
Title | Towards understanding ECG rhythm classification using convolutional neural networks and attention mappings |
Authors | Sebastian D. Goodfellow, Andrew Goodwin, Robert Greer, Peter C. Laussen, Mjaye Mazwi, Danny Eytan |
Abstract | Access to electronic health record (EHR) data has motivated computational advances in medical research. However, various concerns, particularly over privacy, can limit access to and collaborative use of EHR data. Sharing synthetic EHR data could mitigate risk. In this paper, we propose a new approach, medical Generative Adversarial Network (medGAN), to generate realistic synthetic patient records. Based on input real patient records, medGAN can generate high-dimensional discrete variables (e.g., binary and count features) via a combination of an autoencoder and generative adversarial networks. We also propose minibatch averaging to efficiently avoid mode collapse, and increase the learning efficiency with batch normalization and shortcut connections. To demonstrate feasibility, we showed that medGAN generates synthetic patient records that achieve comparable performance to real data on many experiments including distribution statistics, predictive modeling tasks and a medical expert review. We also empirically observe a limited privacy risk in both identity and attribute disclosure using medGAN. |
Tasks | Arrhythmia Detection, ECG Classification, Electrocardiography (ECG) |
Published | 2018-08-17 |
URL | http://proceedings.mlr.press/v85/goodfellow18a.html |
http://proceedings.mlr.press/v85/goodfellow18a/goodfellow18a.pdf | |
PWC | https://paperswithcode.com/paper/towards-understanding-ecg-rhythm |
Repo | https://github.com/Seb-Good/deepecg |
Framework | tf |
Deep Regression Tracking with Shrinkage Loss
Title | Deep Regression Tracking with Shrinkage Loss |
Authors | Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, Ian Reid, Ming-Hsuan Yang |
Abstract | Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions. Due to the potential for fast-tracking and easy implementation, regression trackers have received increasing attention recently. However, state-of-the-art deep regression trackers do not perform as well as discriminative correlation filters (DCFs) trackers. We identify the main bottleneck of training regression networks as extreme foreground-background data imbalance. To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data. Additionally, we apply residual connections to fuse multiple convolutional layers as well as their output response maps. Without bells and whistles, the proposed deep regression tracking method performs favorably against state-of-the-art trackers, especially in comparison with DCFs trackers, on five benchmark datasets including OTB-2013, OTB-2015, Temple-128, UAV-123 and VOT-2016. |
Tasks | |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Xiankai_Lu_Deep_Regression_Tracking_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiankai_Lu_Deep_Regression_Tracking_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/deep-regression-tracking-with-shrinkage-loss |
Repo | https://github.com/chaoma99/DSLT |
Framework | pytorch |
Cliche Expressions in Literary and Genre Novels
Title | Cliche Expressions in Literary and Genre Novels |
Authors | Andreas van Cranenburgh |
Abstract | Should writers {}avoid clich{\'e}s like the plague{''}? Clich{\'e}s are said to be a prominent characteristic of { }low brow{''} literature, and conversely, a negative marker of {``}high brow{''} literature. Clich{'e}s may concern the storyline, the characters, or the style of writing. We focus on clich{'e} expressions, ready-made stock phrases which can be taken as a sign of uncreative writing. We present a corpus study in which we examine to what extent clich{'e} expressions can be attested in a corpus of various kinds of contemporary fiction, based on a large, curated lexicon of clich{'e} expressions. The results show to what extent the negative view on clich{'e}s is supported by data: we find a significant negative correlation of -0.48 between clich{'e} density and literary ratings of texts. We also investigate interactions with genre and characterize the language of clich{'e}s with several basic textual features. Code used for this paper is available at \url{https://github.com/andreasvc/litcliches/} | |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4504/ |
https://www.aclweb.org/anthology/W18-4504 | |
PWC | https://paperswithcode.com/paper/cliche-expressions-in-literary-and-genre |
Repo | https://github.com/andreasvc/litcliches |
Framework | none |
Differentiable Abstract Interpretation for Provably Robust Neural Networks
Title | Differentiable Abstract Interpretation for Provably Robust Neural Networks |
Authors | Matthew Mirman, Timon Gehr, Martin Vechev |
Abstract | We introduce a scalable method for training robust neural networks based on abstract interpretation. We present several abstract transformers which balance efficiency with precision and show these can be used to train large neural networks that are certifiably robust to adversarial perturbations. |
Tasks | |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2477 |
http://proceedings.mlr.press/v80/mirman18b/mirman18b.pdf | |
PWC | https://paperswithcode.com/paper/differentiable-abstract-interpretation-for |
Repo | https://github.com/eth-sri/diffai |
Framework | pytorch |
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
Title | Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection |
Authors | Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, Haifeng Chen |
Abstract | Unsupervised anomaly detection on multi- or high-dimensional data is of great importance in both fundamental machine learning research and industrial applications, for which density estimation lies at the core. Although previous approaches based on dimensionality reduction followed by density estimation have made fruitful progress, they mainly suffer from decoupled model learning with inconsistent optimization goals and incapability of preserving essential information in the low-dimensional space. In this paper, we present a Deep Autoencoding Gaussian Mixture Model (DAGMM) for unsupervised anomaly detection. Our model utilizes a deep autoencoder to generate a low-dimensional representation and reconstruction error for each input data point, which is further fed into a Gaussian Mixture Model (GMM). Instead of using decoupled two-stage training and the standard Expectation-Maximization (EM) algorithm, DAGMM jointly optimizes the parameters of the deep autoencoder and the mixture model simultaneously in an end-to-end fashion, leveraging a separate estimation network to facilitate the parameter learning of the mixture model. The joint optimization, which well balances autoencoding reconstruction, density estimation of latent representation, and regularization, helps the autoencoder escape from less attractive local optima and further reduce reconstruction errors, avoiding the need of pre-training. Experimental results on several public benchmark datasets show that, DAGMM significantly outperforms state-of-the-art anomaly detection techniques, and achieves up to 14% improvement based on the standard F1 score. |
Tasks | Anomaly Detection, Density Estimation, Dimensionality Reduction, Unsupervised Anomaly Detection |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=BJJLHbb0- |
https://openreview.net/pdf?id=BJJLHbb0- | |
PWC | https://paperswithcode.com/paper/deep-autoencoding-gaussian-mixture-model-for |
Repo | https://github.com/danieltan07/dagmm |
Framework | pytorch |
LSTM Neural Network for Textual Ngrams
Title | LSTM Neural Network for Textual Ngrams |
Authors | Shaun C. D’Souza |
Abstract | Cognitive neuroscience is the study of how the human brain functions on tasks like decision making, language, perception and reasoning. Deep learning is a class of machine learning algorithms that use neural networks. They are designed to model the responses of neurons in the human brain. Learning can be supervised or unsupervised. Ngram token models are used extensively in language prediction. Ngrams are probabilistic models that are used in predicting the next word or token. They are a statistical model of word sequences or tokens and are called Language Models or Lms. Ngrams are essential in creating language prediction models. We are exploring a broader sandbox ecosystems enabling for AI. Specifically, around Deep learning applications on unstructured content form on the web. |
Tasks | Decision Making |
Published | 2018-11-26 |
URL | https://www.preprints.org/manuscript/201811.0579/v1 |
https://www.preprints.org/manuscript/201811.0579/v1/download | |
PWC | https://paperswithcode.com/paper/lstm-neural-network-for-textual-ngrams |
Repo | https://github.com/shaundsouza/lstm-textual-ngrams |
Framework | none |
Intracerebral EEG Artifact Identification Using Convolutional Neural Networks
Title | Intracerebral EEG Artifact Identification Using Convolutional Neural Networks |
Authors | Petr Nejedly, Jan Cimbalnik, Petr Klimes, Filip Plesinger, Josef Halamek, Vaclav Kremen, Ivo Viscor, Benjamin H. Brinkmann, Martin Pail, Milan Brazdil, Gregory Worrell, Pavel Jurak |
Abstract | Manual and semi-automatic identification of artifacts and unwanted physiological signals in large intracerebral electroencephalographic (iEEG) recordings is time consuming and inaccurate. To date, unsupervised methods to accurately detect iEEG artifacts are not available. This study introduces a novel machine-learning approach for detection of artifacts in iEEG signals in clinically controlled conditions using convolutional neural networks (CNN) and benchmarks the method’s performance against expert annotations. The method was trained and tested on data obtained from St Anne’s University Hospital (Brno, Czech Republic) and validated on data from Mayo Clinic (Rochester, Minnesota, U.S.A). We show that the proposed technique can be used as a generalized model for iEEG artifact detection. Moreover, a transfer learning process might be used for retraining of the generalized version to form a data-specific model. The generalized model can be efficiently retrained for use with different EEG acquisition systems and noise environments. The generalized and specialized model F1 scores on the testing dataset were 0.81 and 0.96, respectively. The CNN model provides faster, more objective, and more reproducible iEEG artifact detection compared to manual approaches. |
Tasks | EEG, EEG Artifact Removal, Transfer Learning |
Published | 2018-08-13 |
URL | https://doi.org/10.1007/s12021-018-9397-6 |
https://link.springer.com/content/pdf/10.1007%2Fs12021-018-9397-6.pdf | |
PWC | https://paperswithcode.com/paper/intracerebral-eeg-artifact-identification |
Repo | https://github.com/xnejed07/NoiseDetectionCNN |
Framework | none |
Eclipse CDT code analysis and unit testing
Title | Eclipse CDT code analysis and unit testing |
Authors | Shaun C. D’Souza |
Abstract | In this paper we look at the Eclipse IDE and its support for CDT (C/C++ Development Tools). Eclipse is an open source IDE and supports a variety of programming languages including plugin functionality. Eclipse supports the standard GNU environment for compiling, building and debugging applications. The CDT is a plugin which enables development of C/C++ applications in eclipse. It enables functionality including code browsing, syntax highlighting and code completion. We verify a 50X improvement in LOC automation for Fake class .cpp / .h and class test .cpp code generation. |
Tasks | Code Generation |
Published | 2018-11-15 |
URL | https://peerj.com/preprints/27350/ |
https://peerj.com/preprints/27350.pdf | |
PWC | https://paperswithcode.com/paper/eclipse-cdt-code-analysis-and-unit-testing |
Repo | https://github.com/shaundsouza/eclipse-cdt |
Framework | none |