January 30, 2020

3173 words 15 mins read

Paper Group ANR 421

Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction. A Review on Neural Network Models of Schizophrenia and Autism Spectrum Disorder. Intelligent Active Queue Management Using Explicit Congestion Notification. I Can See Clearly Now : Image Restoration via De-Raining. LSTM Networks Can Perform Dynamic Counting …

Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction


Title	Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction
Authors	Longhao Yuan, Chao Li, Jianting Cao, Qibin Zhao
Abstract	Dimensionality reduction is an essential technique for multi-way large-scale data, i.e., tensor. Tensor ring (TR) decomposition has become popular due to its high representation ability and flexibility. However, the traditional TR decomposition algorithms suffer from high computational cost when facing large-scale data. In this paper, taking advantages of the recently proposed tensor random projection method, we propose two TR decomposition algorithms. By employing random projection on every mode of the large-scale tensor, the TR decomposition can be processed at a much smaller scale. The simulation experiment shows that the proposed algorithms are $4-25$ times faster than traditional algorithms without loss of accuracy, and our algorithms show superior performance in deep learning dataset compression and hyperspectral image reconstruction experiments compared to other randomized algorithms.
Tasks	Dimensionality Reduction, Image Reconstruction
Published	2019-01-07
URL	http://arxiv.org/abs/1901.01652v1
PDF	http://arxiv.org/pdf/1901.01652v1.pdf
PWC	https://paperswithcode.com/paper/randomized-tensor-ring-decomposition-and-its
Repo
Framework

A Review on Neural Network Models of Schizophrenia and Autism Spectrum Disorder


Title	A Review on Neural Network Models of Schizophrenia and Autism Spectrum Disorder
Authors	Pablo Lanillos, Daniel Oliva, Anja Philippsen, Yuichi Yamashita, Yukie Nagai, Gordon Cheng
Abstract	This survey presents the most relevant neural network models of autism spectrum disorder and schizophrenia, from the first connectionist models to recent deep network architectures. We analyzed and compared the most representative symptoms with its neural model counterpart, detailing the alteration introduced in the network that generates each of the symptoms, and identifying their strengths and weaknesses. We additionally cross-compared Bayesian and free-energy approaches, as they are widely applied to modeling psychiatric disorders and share basic mechanisms with neural networks. Models of schizophrenia mainly focused on hallucinations and delusional thoughts using neural dysconnections or inhibitory imbalance as the predominating alteration. Models of autism rather focused on perceptual difficulties, mainly excessive attention to environment details, implemented as excessive inhibitory connections or increased sensory precision. We found an excessive tight view of the psychopathologies around one specific and simplified effect, usually constrained to the technical idiosyncrasy of the used network architecture. Recent theories and evidence on sensorimotor integration and body perception combined with modern neural network architectures could offer a broader and novel spectrum to approach these psychopathologies. This review emphasizes the power of artificial neural networks for modeling some symptoms of neurological disorders but also calls for further developing these techniques in the field of computational psychiatry.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10015v2
PDF	https://arxiv.org/pdf/1906.10015v2.pdf
PWC	https://paperswithcode.com/paper/a-review-on-neural-network-models-of
Repo
Framework

Intelligent Active Queue Management Using Explicit Congestion Notification


Title	Intelligent Active Queue Management Using Explicit Congestion Notification
Authors	Cesar A. Gomez, Xianbin Wang, Abdallah Shami
Abstract	As more end devices are getting connected, the Internet will become more congested. Various congestion control techniques have been developed either on transport or network layers. Active Queue Management (AQM) is a paradigm that aims to mitigate the congestion on the network layer through active buffer control to avoid overflow. However, finding the right parameters for an AQM scheme is challenging, due to the complexity and dynamics of the networks. On the other hand, the Explicit Congestion Notification (ECN) mechanism is a solution that makes visible incipient congestion on the network layer to the transport layer. In this work, we propose to exploit the ECN information to improve AQM algorithms by applying Machine Learning techniques. Our intelligent method uses an artificial neural network to predict congestion and an AQM parameter tuner based on reinforcement learning. The evaluation results show that our solution can enhance the performance of deployed AQM, using the existing TCP congestion control mechanisms.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1909.08386v1
PDF	https://arxiv.org/pdf/1909.08386v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-active-queue-management-using
Repo
Framework

I Can See Clearly Now : Image Restoration via De-Raining


Title	I Can See Clearly Now : Image Restoration via De-Raining
Authors	Horia Porav, Tom Bruls, Paul Newman
Abstract	We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that allows one lens to be affected by real water droplets while keeping the other lens clear. We train a denoising generator using this dataset and show that it is effective at removing the effect of real water droplets, in the context of image reconstruction and road marking segmentation. To further test our de-noising approach, we describe a method of adding computer-generated adherent water droplets and streaks to any images, and use this technique as a proxy to demonstrate the effectiveness of our model in the context of general semantic segmentation. We benchmark our results using the CamVid road marking segmentation dataset, Cityscapes semantic segmentation datasets and our own real-rain dataset, and show significant improvement on all tasks.
Tasks	Denoising, Image Reconstruction, Image Restoration, Semantic Segmentation
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00893v1
PDF	http://arxiv.org/pdf/1901.00893v1.pdf
PWC	https://paperswithcode.com/paper/i-can-see-clearly-now-image-restoration-via
Repo
Framework

LSTM Networks Can Perform Dynamic Counting


Title	LSTM Networks Can Perform Dynamic Counting
Authors	Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov, Stuart M. Shieber
Abstract	In this paper, we systematically assess the ability of standard recurrent networks to perform dynamic counting and to encode hierarchical representations. All the neural models in our experiments are designed to be small-sized networks both to prevent them from memorizing the training sets and to visualize and interpret their behaviour at test time. Our results demonstrate that the Long Short-Term Memory (LSTM) networks can learn to recognize the well-balanced parenthesis language (Dyck-$1$) and the shuffles of multiple Dyck-$1$ languages, each defined over different parenthesis-pairs, by emulating simple real-time $k$-counter machines. To the best of our knowledge, this work is the first study to introduce the shuffle languages to analyze the computational power of neural networks. We also show that a single-layer LSTM with only one hidden unit is practically sufficient for recognizing the Dyck-$1$ language. However, none of our recurrent networks was able to yield a good performance on the Dyck-$2$ language learning task, which requires a model to have a stack-like mechanism for recognition.
Tasks
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03648v1
PDF	https://arxiv.org/pdf/1906.03648v1.pdf
PWC	https://paperswithcode.com/paper/lstm-networks-can-perform-dynamic-counting
Repo
Framework

A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems


Title	A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems
Authors	Frank van Harmelen, Annette ten Teije
Abstract	We propose a set of compositional design patterns to describe a large variety of systems that combine statistical techniques from machine learning with symbolic techniques from knowledge representation. As in other areas of computer science (knowledge engineering, software engineering, ontology engineering, process mining and others), such design patterns help to systematize the literature, clarify which combinations of techniques serve which purposes, and encourage re-use of software components. We have validated our set of compositional design patterns against a large body of recent literature.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12389v1
PDF	https://arxiv.org/pdf/1905.12389v1.pdf
PWC	https://paperswithcode.com/paper/a-boxology-of-design-patterns-for-hybrid
Repo
Framework

MGpi: A Computational Model of Multiagent Group Perception and Interaction


Title	MGpi: A Computational Model of Multiagent Group Perception and Interaction
Authors	Navyata Sanghvi, Ryo Yonetani, Kris Kitani
Abstract	Toward enabling next-generation robots capable of socially intelligent interaction with humans, we present a $\mathbf{computational; model}$ of interactions in a social environment of multiple agents and multiple groups. The Multiagent Group Perception and Interaction (MGpi) network is a deep neural network that predicts the appropriate social action to execute in a group conversation (e.g., speak, listen, respond, leave), taking into account neighbors’ observable features (e.g., location of people, gaze orientation, distraction, etc.). A central component of MGpi is the Kinesic-Proxemic-Message (KPM) gate, that performs social signal gating to extract important information from a group conversation. In particular, KPM gate filters incoming social cues from nearby agents by observing their body gestures (kinesics) and spatial behavior (proxemics). The MGpi network and its KPM gate are learned via imitation learning, using demonstrations from our designed $\mathbf{social; interaction; simulator}$. Further, we demonstrate the efficacy of the KPM gate as a social attention mechanism, achieving state-of-the-art performance on the task of $\mathbf{group; identification}$ without using explicit group annotations, layout assumptions, or manually chosen parameters.
Tasks	Imitation Learning
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01537v2
PDF	https://arxiv.org/pdf/1903.01537v2.pdf
PWC	https://paperswithcode.com/paper/modeling-social-group-communication-with
Repo
Framework

AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning


Title	AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
Authors	Lu Chen, Zhi Chen, Bowen Tan, Sishan Long, Milica Gasic, Kai Yu
Abstract	Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: 1) Many DRL-based policies are not sample-efficient. 2) Most models don’t have the capability of policy transfer between different domains. In this paper, we propose a universal framework, AgentGraph, to tackle these two problems. The proposed AgentGraph is the combination of GNN-based architecture and DRL-based algorithm. It can be regarded as one of the multi-agent reinforcement learning approaches. Each agent corresponds to a node in a graph, which is defined according to the dialogue domain ontology. When making a decision, each agent can communicate with its neighbors on the graph. Under AgentGraph framework, we further propose Dual GNN-based dialogue policy, which implicitly decomposes the decision in each turn into a high-level global decision and a low-level local decision. Experiments show that AgentGraph models significantly outperform traditional reinforcement learning approaches on most of the 18 tasks of the PyDial benchmark. Moreover, when transferred from the source task to a target task, these models not only have acceptable initial performance but also converge much faster on the target task.
Tasks	Dialogue Management, Multi-agent Reinforcement Learning, Spoken Dialogue Systems
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11259v1
PDF	https://arxiv.org/pdf/1905.11259v1.pdf
PWC	https://paperswithcode.com/paper/agentgraph-towards-universal-dialogue
Repo
Framework

Collaborative Machine Learning Markets with Data-Replication-Robust Payments


Title	Collaborative Machine Learning Markets with Data-Replication-Robust Payments
Authors	Olga Ohrimenko, Shruti Tople, Sebastian Tschiatschek
Abstract	We study the problem of collaborative machine learning markets where multiple parties can achieve improved performance on their machine learning tasks by combining their training data. We discuss desired properties for these machine learning markets in terms of fair revenue distribution and potential threats, including data replication. We then instantiate a collaborative market for cases where parties share a common machine learning task and where parties’ tasks are different. Our marketplace incentivizes parties to submit high quality training and true validation data. To this end, we introduce a novel payment division function that is robust-to-replication and customized output models that perform well only on requested machine learning tasks. In experiments, we validate the assumptions underlying our theoretical analysis and show that these are approximately satisfied for commonly used machine learning models.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.09052v1
PDF	https://arxiv.org/pdf/1911.09052v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-machine-learning-markets-with
Repo
Framework

Recurrent neural network based decision support system


Title	Recurrent neural network based decision support system
Authors	Abiodun Ayodeji, Yong-kuo Liu
Abstract	Decision Support Systems (DSS) in complex installations play a crucial role in assisting operators in decision making during abnormal transients and process disturbances, by actively displaying the status of the system and recording events, time of occurrence and suggesting relevant actions. The complexity and dynamics of complex systems require a careful selection of suitable neural network architecture, so as to improve diagnostic accuracy. In this work, we present a technique to develop a fault diagnostic decision support using recurrent neural network and Principal Component Analysis (PCA). We utilized the PCA method for noise filtering in the pre-diagnostic stage, and evaluate the predictive capability of radial basis recurrent network on a representative data derived from the simulation of a pressurized nuclear reactor. The process was validated using data from different fault scenarios, and the fault signatures were used as the input. The predictive outputs required are the location and sizes of the faults. The result shows that the radial basis network gives accurate predictions. Selected hyperparameters and diagnostic results are also presented in this paper.
Tasks	Decision Making
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02219v1
PDF	https://arxiv.org/pdf/1910.02219v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-neural-network-based-decision
Repo
Framework

The Group Loss for Deep Metric Learning


Title	The Group Loss for Deep Metric Learning
Authors	Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe
Abstract	Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that “similar objects should belong to the same group”, the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles
Tasks	Image Retrieval, Metric Learning
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00385v3
PDF	https://arxiv.org/pdf/1912.00385v3.pdf
PWC	https://paperswithcode.com/paper/the-group-loss-for-deep-metric-learning
Repo
Framework

An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms


Title	An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms
Authors	Ruoxi Jia, Xuehui Sun, Jiacen Xu, Ce Zhang, Bo Li, Dawn Song
Abstract	This paper focuses on valuating training data for supervised learning tasks and studies the Shapley value, a data value notion originated in cooperative game theory. The Shapley value defines a unique value distribution scheme that satisfies a set of appealing properties desired by a data value notion. However, the Shapley value requires exponential complexity to calculate exactly. Existing approximation algorithms, although achieving great improvement over the exact algorithm, relies on retraining models for multiple times, thus remaining limited when applied to larger-scale learning tasks and real-world datasets. In this work, we develop a simple and efficient heuristic for data valuation based on the Shapley value with complexity independent with the model size. The key idea is to approximate the model via a $K$-nearest neighbor ($K$NN) classifier, which has a locality structure that can lead to efficient Shapley value calculation. We evaluate the utility of the values produced by the $K$NN proxies in various settings, including label noise correction, watermark detection, data summarization, active data acquisition, and domain adaption. Extensive experiments demonstrate that our algorithm achieves at least comparable utility to the values produced by existing algorithms while significant efficiency improvement. Moreover, we theoretically analyze the Shapley value and justify its advantage over the leave-one-out error as a data value measure.
Tasks	Data Summarization, Domain Adaptation
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07128v1
PDF	https://arxiv.org/pdf/1911.07128v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-and-comparative-analysis-of-data-1
Repo
Framework

Predicting the Outcome of Judicial Decisions made by the European Court of Human Rights


Title	Predicting the Outcome of Judicial Decisions made by the European Court of Human Rights
Authors	Conor O’Sullivan, Joeran Beel
Abstract	In this study, machine learning models were constructed to predict whether judgments made by the European Court of Human Rights (ECHR) would lead to a violation of an Article in the Convention on Human Rights. The problem is framed as a binary classification task where a judgment can lead to a “violation” or “non-violation” of a particular Article. Using auto-sklearn, an automated algorithm selection package, models were constructed for 12 Articles in the Convention. To train these models, textual features were obtained from the ECHR Judgment documents using N-grams, word embeddings and paragraph embeddings. Additional documents, from the ECHR, were incorporated into the models through the creation of a word embedding (echr2vec) and a doc2vec model. The features obtained using the echr2vec embedding provided the highest cross-validation accuracy for 5 of the Articles. The overall test accuracy, across the 12 Articles, was 68.83%. As far as we could tell, this is the first estimate of the accuracy of such machine learning models using a realistic test set. This provides an important benchmark for future work. As a baseline, a simple heuristic of always predicting the most common outcome in the past was used. The heuristic achieved an overall test accuracy of 86.68% which is 29.7% higher than the models. Again, this was seemingly the first study that included such a heuristic with which to compare model results. The higher accuracy achieved by the heuristic highlights the importance of including such a baseline.
Tasks	Word Embeddings
Published	2019-12-16
URL	https://arxiv.org/abs/1912.10819v1
PDF	https://arxiv.org/pdf/1912.10819v1.pdf
PWC	https://paperswithcode.com/paper/predicting-the-outcome-of-judicial-decisions
Repo
Framework

TMLab SRPOL at SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums


Title	TMLab SRPOL at SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums
Authors	Piotr Niewinski, Aleksander Wawer, Maria Pszona, Maria Janicka
Abstract	The article describes our submission to SemEval 2019 Task 8 on Fact-Checking in Community Forums. The systems under discussion participated in Subtask A: decide whether a question asks for factual information, opinion/advice or is just socializing. Our primary submission was ranked as the second one among all participants in the official evaluation phase. The article presents our primary solution: Deeply Regularized Residual Neural Network (DRR NN) with Universal Sentence Encoder embeddings. This is followed by a description of two contrastive solutions based on ensemble methods.
Tasks	Community Question Answering, Question Answering
Published	2019-05-29
URL	https://arxiv.org/abs/1906.01515v1
PDF	https://arxiv.org/pdf/1906.01515v1.pdf
PWC	https://paperswithcode.com/paper/190601515
Repo
Framework

Disentangling Monocular 3D Object Detection


Title	Disentangling Monocular 3D Object Detection
Authors	Andrea Simonelli, Samuel Rota Rota Bulò, Lorenzo Porzi, Manuel López-Antequera, Peter Kontschieder
Abstract	In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes. Our proposed loss disentanglement has the twofold advantage of simplifying the training dynamics in the presence of losses with complex interactions of parameters, and sidestepping the issue of balancing independent regression terms. Our solution overcomes these issues by isolating the contribution made by groups of parameters to a given loss, without changing its nature. We further apply loss disentanglement to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. Besides our methodological innovations, we critically review the AP metric used in KITTI3D, which emerged as the most important dataset for comparing 3D detection results. We identify and resolve a flaw in the 11-point interpolated AP metric, affecting all previously published detection results and particularly biases the results of monocular 3D detection. We provide extensive experimental evaluations and ablation studies on the KITTI3D and nuScenes datasets, setting new state-of-the-art results on object category car by large margins.
Tasks	3D Object Detection, Object Detection
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12365v1
PDF	https://arxiv.org/pdf/1905.12365v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-monocular-3d-object-detection
Repo
Framework