January 27, 2020

3339 words 16 mins read

Paper Group ANR 1219

Beyond 5G: Leveraging Cell Free TDD Massive MIMO using Cascaded Deep learning. Model Agnostic Contrastive Explanations for Structured Data. Support Vector Machine Classifier via $L_{0/1}$ Soft-Margin Loss. Customizable Architecture Search for Semantic Segmentation. Cross-Modal Self-Attention Network for Referring Image Segmentation. Facial Pose Est …

Beyond 5G: Leveraging Cell Free TDD Massive MIMO using Cascaded Deep learning


Title	Beyond 5G: Leveraging Cell Free TDD Massive MIMO using Cascaded Deep learning
Authors	Navaneet Athreya, Vishnu Raj, Sheetal Kalyani
Abstract	Cell Free Massive MIMO is a solution for improving the spectral efficiency of next generation communication systems and a crucial aspect for realizing the gains of the technology is the availability of accurate Channel State Information (CSI). Time Division Duplexing (TDD) mode is popular for Cell Free Massive MIMO since the physical wireless channel’s assumed reciprocity facilitates channel estimation. However, the availability of accurate CSI in the TDD mode is hindered by the non reciprocity of the end to end channel, due to the presence of RF components, as well as the non availability of CSI in the subcarriers that do not have reference signals. Hence, the prediction of the Downlink CSI in the subcarriers without reference signals becomes an even more complicated problem. In this work, we consider TDD non-reciprocity with limited availability of resource elements for CSI estimation and propose a deep learning based approach using cascaded Deep Neural Networks (DNNs) to attain a one shot prediction of the reverse channel across the entire bandwidth. The proposed method is able to estimate downlink CSI at all subcarriers from the uplink CSI at selected subcarriers and hence does not require downlink CSI feedback.
Tasks
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05705v1
PDF	https://arxiv.org/pdf/1910.05705v1.pdf
PWC	https://paperswithcode.com/paper/beyond-5g-leveraging-cell-free-tdd-massive
Repo
Framework

Model Agnostic Contrastive Explanations for Structured Data


Title	Model Agnostic Contrastive Explanations for Structured Data
Authors	Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, Ruchir Puri
Abstract	Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for \emph{any} classification model where one is able to \emph{only} query the class probabilities for a desired input. This allows us to generate contrastive explanations for not only neural networks, but models such as random forests, boosted trees and even arbitrary ensembles that are still amongst the state-of-the-art when learning on structured data [13]. Moreover, to obtain meaningful explanations we propose a principled approach to handle real and categorical features leading to novel formulations for computing pertinent positives and negatives that form the essence of a contrastive explanation. A detailed treatment of the different data types of this nature was not performed in the previous work, which assumed all features to be positive real valued with zero being indicative of the least interesting value. We part with this strong implicit assumption and generalize these methods so as to be applicable across a much wider range of problem settings. We quantitatively and qualitatively validate our approach over 5 public datasets covering diverse domains.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00117v1
PDF	https://arxiv.org/pdf/1906.00117v1.pdf
PWC	https://paperswithcode.com/paper/190600117
Repo
Framework

Support Vector Machine Classifier via $L_{0/1}$ Soft-Margin Loss


Title	Support Vector Machine Classifier via $L_{0/1}$ Soft-Margin Loss
Authors	Huajun Wang, Yuanhai Shao, Shenglong Zhou, Ce Zhang, Naihua Xiu
Abstract	Support vector machine (SVM) has attracted great attentions for the last two decades due to its extensive applications, and thus numerous optimization models have been proposed. To distinguish all of them, in this paper, we introduce a new model equipped with an $L_{0/1}$ soft-margin loss (dubbed as $L_{0/1}$-SVM) which well captures the nature of the binary classification. Many of the existing convex/non-convex soft-margin losses can be viewed as a surrogate of the $L_{0/1}$ soft-margin loss. Despite the discrete nature of $L_{0/1}$, we manage to establish the existence of global minimizer of the new model as well as revealing the relationship among its minimizers and KKT/P-stationary points. These theoretical properties allow us to take advantage of the alternating direction method of multipliers. In addition, the $L_{0/1}$-support vector operator is introduced as a filter to prevent outliers from being support vectors during the training process. Hence, the method is expected to be relatively robust. Finally, numerical experiments demonstrate that our proposed method generates better performance in terms of much shorter computational time with much fewer number of support vectors when against with some other leading methods in areas of SVM. When the data size gets bigger, its advantage becomes more evident.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07418v1
PDF	https://arxiv.org/pdf/1912.07418v1.pdf
PWC	https://paperswithcode.com/paper/support-vector-machine-classifier-via-l_01
Repo
Framework

Customizable Architecture Search for Semantic Segmentation


Title	Customizable Architecture Search for Semantic Segmentation
Authors	Yiheng Zhang, Zhaofan Qiu, Jingen Liu, Ting Yao, Dong Liu, Tao Mei
Abstract	In this paper, we propose a Customizable Architecture Search (CAS) approach to automatically generate a network architecture for semantic image segmentation. The generated network consists of a sequence of stacked computation cells. A computation cell is represented as a directed acyclic graph, in which each node is a hidden representation (i.e., feature map) and each edge is associated with an operation (e.g., convolution and pooling), which transforms data to a new layer. During the training, the CAS algorithm explores the search space for an optimized computation cell to build a network. The cells of the same type share one architecture but with different weights. In real applications, however, an optimization may need to be conducted under some constraints such as GPU time and model size. To this end, a cost corresponding to the constraint will be assigned to each operation. When an operation is selected during the search, its associated cost will be added to the objective. As a result, our CAS is able to search an optimized architecture with customized constraints. The approach has been thoroughly evaluated on Cityscapes and CamVid datasets, and demonstrates superior performance over several state-of-the-art techniques. More remarkably, our CAS achieves 72.3% mIoU on the Cityscapes dataset with speed of 108 FPS on an Nvidia TitanXp GPU.
Tasks	Semantic Segmentation
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09550v1
PDF	https://arxiv.org/pdf/1908.09550v1.pdf
PWC	https://paperswithcode.com/paper/customizable-architecture-search-for-semantic-1
Repo
Framework


Title	Cross-Modal Self-Attention Network for Referring Image Segmentation
Authors	Linwei Ye, Mrigank Rochan, Zhi Liu, Yang Wang
Abstract	We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the input image. In addition, we propose a gated multi-level fusion module to selectively integrate self-attentive cross-modal features corresponding to different levels in the image. This module controls the information flow of features at different levels. We validate the proposed approach on four evaluation datasets. Our proposed approach consistently outperforms existing state-of-the-art methods.
Tasks	Semantic Segmentation
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04745v1
PDF	http://arxiv.org/pdf/1904.04745v1.pdf
PWC	https://paperswithcode.com/paper/cross-modal-self-attention-network-for
Repo
Framework

Facial Pose Estimation by Deep Learning from Label Distributions


Title	Facial Pose Estimation by Deep Learning from Label Distributions
Authors	Zhaoxiang Liu, Zezhou Chen, Jinqiang Bai, Shaohua Li, Shiguo Lian
Abstract	Facial pose estimation has gained a lot of attentions in many practical applications, such as human-robot interaction, gaze estimation and driver monitoring. Meanwhile, end-to-end deep learning-based facial pose estimation is becoming more and more popular. However, facial pose estimation suffers from a key challenge: the lack of sufficient training data for many poses, especially for large poses. Inspired by the observation that the faces under close poses look similar, we reformulate the facial pose estimation as a label distribution learning problem, considering each face image as an example associated with a Gaussian label distribution rather than a single label, and construct a convolutional neural network which is trained with a multi-loss function on AFLW dataset and 300W-LP dataset to predict the facial poses directly from color image. Extensive experiments are conducted on several popular benchmarks, including AFLW2000, BIWI, AFLW and AFW, where our approach shows a significant advantage over other state-of-the-art methods.
Tasks	Gaze Estimation, Pose Estimation
Published	2019-04-30
URL	https://arxiv.org/abs/1904.13102v3
PDF	https://arxiv.org/pdf/1904.13102v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-face-pose-recovery
Repo
Framework

On the equivalence between graph isomorphism testing and function approximation with GNNs


Title	On the equivalence between graph isomorphism testing and function approximation with GNNs
Authors	Zhengdao Chen, Soledad Villar, Lei Chen, Joan Bruna
Abstract	Graph neural networks (GNNs) have achieved lots of success on graph-structured data. In the light of this, there has been increasing interest in studying their representation power. One line of work focuses on the universal approximation of permutation-invariant functions by certain classes of GNNs, and another demonstrates the limitation of GNNs via graph isomorphism tests. Our work connects these two perspectives and proves their equivalence. We further develop a framework of the representation power of GNNs with the language of sigma-algebra, which incorporates both viewpoints. Using this framework, we compare the expressive power of different classes of GNNs as well as other methods on graphs. In particular, we prove that order-2 Graph G-invariant networks fail to distinguish non-isomorphic regular graphs with the same degree. We then extend them to a new architecture, Ring-GNNs, which succeeds on distinguishing these graphs and provides improvements on real-world social network datasets.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12560v1
PDF	https://arxiv.org/pdf/1905.12560v1.pdf
PWC	https://paperswithcode.com/paper/on-the-equivalence-between-graph-isomorphism
Repo
Framework

QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning


Title	QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning
Authors	Nof Abuzainab, Tugba Erpek, Kemal Davaslioglu, Yalin E. Sagduyu, Yi Shi, Sharon J. Mackey, Mitesh Patel, Frank Panettieri, Muhammad A. Qureshi, Volkan Isler, Aylin Yener
Abstract	The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks. To ensure robust communication against jamming, an interference-aware routing protocol is developed that allows nodes to avoid communication holes created by jamming attacks. Then, a distributed cooperation framework, based on deep reinforcement learning, is proposed that allows nodes to assess network conditions and make deep learning-driven, distributed, and real-time decisions on whether to participate in data communications, defend the network against jamming and eavesdropping attacks, or jam other transmissions. The objective is to maximize the network performance that incorporates throughput, energy efficiency, delay, and security metrics. Simulation results show that the proposed jamming-aware routing approach is robust against jamming and when throughput is prioritized, the proposed deep reinforcement learning approach can achieve significant (measured as three-fold) increase in throughput, compared to a benchmark policy with fixed roles assigned to nodes.
Tasks
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05766v1
PDF	https://arxiv.org/pdf/1910.05766v1.pdf
PWC	https://paperswithcode.com/paper/qos-and-jamming-aware-wireless-networking
Repo
Framework

Multifaceted 4D Feature Segmentation and Extraction in Point and Field-based Datasets


Title	Multifaceted 4D Feature Segmentation and Extraction in Point and Field-based Datasets
Authors	Franz Sauer, Kwan-Liu Ma
Abstract	The use of large-scale multifaceted data is common in a wide variety of scientific applications. In many cases, this multifaceted data takes the form of a field-based (Eulerian) and point/trajectory-based (Lagrangian) representation as each has a unique set of advantages in characterizing a system of study. Furthermore, studying the increasing scale and complexity of these multifaceted datasets is limited by perceptual ability and available computational resources, necessitating sophisticated data reduction and feature extraction techniques. In this work, we present a new 4D feature segmentation/extraction scheme that can operate on both the field and point/trajectory data types simultaneously. The resulting features are time-varying data subsets that have both a field and point-based component, and were extracted based on underlying patterns from both data types. This enables researchers to better explore both the spatial and temporal interplay between the two data representations and study underlying phenomena from new perspectives. We parallelize our approach using GPU acceleration and apply it to real world multifaceted datasets to illustrate the types of features that can be extracted and explored.
Tasks
Published	2019-03-28
URL	http://arxiv.org/abs/1903.12294v1
PDF	http://arxiv.org/pdf/1903.12294v1.pdf
PWC	https://paperswithcode.com/paper/multifaceted-4d-feature-segmentation-and
Repo
Framework

LACI: Low-effort Automatic Calibration of Infrastructure Sensors


Title	LACI: Low-effort Automatic Calibration of Infrastructure Sensors
Authors	Johannes Müller, Martin Herrmann, Jan Strohbeck, Vasileios Belagiannis, Michael Buchholz
Abstract	Sensor calibration usually is a time consuming yet important task. While classical approaches are sensor-specific and often need calibration targets as well as a widely overlapping field of view (FOV), within this work, a cooperative intelligent vehicle is used as callibration target. The vehicleis detected in the sensor frame and then matched with the information received from the cooperative awareness messagessend by the coperative intelligent vehicle. The presented algorithm is fully automated as well as sensor-independent, relying only on a very common set of assumptions. Due to the direct registration on the world frame, no overlapping FOV is necessary. The algorithm is evaluated through experiment for four laserscanners as well as one pair of stereo cameras showing a repetition error within the measurement uncertainty of the sensors. A plausibility check rules out systematic errors that might not have been covered by evaluating the repetition error.
Tasks	Calibration
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01711v1
PDF	https://arxiv.org/pdf/1911.01711v1.pdf
PWC	https://paperswithcode.com/paper/laci-low-effort-automatic-calibration-of
Repo
Framework

Reliable Deep Grade Prediction with Uncertainty Estimation


Title	Reliable Deep Grade Prediction with Uncertainty Estimation
Authors	Qian Hu, Huzefa Rangwala
Abstract	Currently, college-going students are taking longer to graduate than their parental generations. Further, in the United States, the six-year graduation rate has been 59% for decades. Improving the educational quality by training better-prepared students who can successfully graduate in a timely manner is critical. Accurately predicting students’ grades in future courses has attracted much attention as it can help identify at-risk students early so that personalized feedback can be provided to them on time by advisors. Prior research on students’ grade prediction include shallow linear models; however, students’ learning is a highly complex process that involves the accumulation of knowledge across a sequence of courses that can not be sufficiently modeled by these linear models. In addition to that, prior approaches focus on prediction accuracy without considering prediction uncertainty, which is essential for advising and decision making. In this work, we present two types of Bayesian deep learning models for grade prediction. The MLP ignores the temporal dynamics of students’ knowledge evolution. Hence, we propose RNN for students’ performance prediction. To evaluate the performance of the proposed models, we performed extensive experiments on data collected from a large public university. The experimental results show that the proposed models achieve better performance than prior state-of-the-art approaches. Besides more accurate results, Bayesian deep learning models estimate uncertainty associated with the predictions. We explore how uncertainty estimation can be applied towards developing a reliable educational early warning system. In addition to uncertainty, we also develop an approach to explain the prediction results, which is useful for advisors to provide personalized feedback to students.
Tasks	Decision Making
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10213v1
PDF	http://arxiv.org/pdf/1902.10213v1.pdf
PWC	https://paperswithcode.com/paper/reliable-deep-grade-prediction-with
Repo
Framework

A self-organising eigenspace map for time series clustering


Title	A self-organising eigenspace map for time series clustering
Authors	Donya Rahmani, Damien Fay, Jacek Brodzki
Abstract	This paper presents a novel time series clustering method, the self-organising eigenspace map (SOEM), based on a generalisation of the well-known self-organising feature map (SOFM). The SOEM operates on the eigenspaces of the embedded covariance structures of time series which are related directly to modes in those time series. Approximate joint diagonalisation acts as a pseudo-metric across these spaces allowing us to generalise the SOFM to a neural network with matrix input. The technique is empirically validated against three sets of experiments; univariate and multivariate time series clustering, and application to (clustered) multi-variate time series forecasting. Results indicate that the technique performs a valid topologically ordered clustering of the time series. The clustering is superior in comparison to standard benchmarks when the data is non-aligned, gives the best clustering stage for when used in forecasting, and can be used with partial/non-overlapping time series, multivariate clustering and produces a topological representation of the time series objects.
Tasks	Time Series, Time Series Clustering, Time Series Forecasting
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05540v1
PDF	https://arxiv.org/pdf/1905.05540v1.pdf
PWC	https://paperswithcode.com/paper/a-self-organising-eigenspace-map-for-time
Repo
Framework

Towards a Framework Combining Machine Ethics and Machine Explainability


Title	Towards a Framework Combining Machine Ethics and Machine Explainability
Authors	Kevin Baum, Holger Hermanns, Timo Speith
Abstract	We find ourselves surrounded by a rapidly increasing number of autonomous and semi-autonomous systems. Two grand challenges arise from this development: Machine Ethics and Machine Explainability. Machine Ethics, on the one hand, is concerned with behavioral constraints for systems, so that morally acceptable, restricted behavior results; Machine Explainability, on the other hand, enables systems to explain their actions and argue for their decisions, so that human users can understand and justifiably trust them. In this paper, we try to motivate and work towards a framework combining Machine Ethics and Machine Explainability. Starting from a toy example, we detect various desiderata of such a framework and argue why they should and how they could be incorporated in autonomous systems. Our main idea is to apply a framework of formal argumentation theory both, for decision-making under ethical constraints and for the task of generating useful explanations given only limited knowledge of the world. The result of our deliberations can be described as a first version of an ethically motivated, principle-governed framework combining Machine Ethics and Machine Explainability
Tasks	Decision Making
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00590v1
PDF	http://arxiv.org/pdf/1901.00590v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-framework-combining-machine-ethics
Repo
Framework

Harnessing the richness of the linguistic signal in predicting pragmatic inferences


Title	Harnessing the richness of the linguistic signal in predicting pragmatic inferences
Authors	Sebastian Schuster, Yuxing Chen, Judith Degen
Abstract	The strength of pragmatic inferences systematically depends on linguistic and contextual cues. For example, the presence of a partitive construction increases the strength of a so-called scalar inference: humans perceive the inference that Chris did not eat all of the cookies to be stronger after hearing “Chris ate some of the cookies” than after hearing the same utterance without a partitive, “Chris ate some cookies”. In this work, we explore to what extent it is possible to learn associations between linguistic cues and inference strength ratings without direct supervision. We show that an LSTM-based sentence encoder with an attention mechanism trained on a dataset of human inference strength ratings is able to predict ratings with high accuracy (r=0.78). We probe the model’s behavior in multiple analyses using corpus data and manually constructed minimal pairs and find that the model learns associations between linguistic cues and scalar inferences, suggesting that these associations are inferable from statistical input.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14254v1
PDF	https://arxiv.org/pdf/1910.14254v1.pdf
PWC	https://paperswithcode.com/paper/harnessing-the-richness-of-the-linguistic
Repo
Framework

Stand-Alone Self-Attention in Vision Models


Title	Stand-Alone Self-Attention in Vision Models
Authors	Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello, Anselm Levskaya, Jonathon Shlens
Abstract	Convolutions are a fundamental building block of modern computer vision systems. Recent approaches have argued for going beyond convolutions in order to capture long-range dependencies. These efforts focus on augmenting convolutional models with content-based interactions, such as self-attention and non-local means, to achieve gains on a number of vision tasks. The natural question that arises is whether attention can be a stand-alone primitive for vision models instead of serving as just an augmentation on top of convolutions. In developing and testing a pure self-attention vision model, we verify that self-attention can indeed be an effective stand-alone layer. A simple procedure of replacing all instances of spatial convolutions with a form of self-attention applied to ResNet model produces a fully self-attentional model that outperforms the baseline on ImageNet classification with 12% fewer FLOPS and 29% fewer parameters. On COCO object detection, a pure self-attention model matches the mAP of a baseline RetinaNet while having 39% fewer FLOPS and 34% fewer parameters. Detailed ablation studies demonstrate that self-attention is especially impactful when used in later layers. These results establish that stand-alone self-attention is an important addition to the vision practitioner’s toolbox.
Tasks	Object Detection
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05909v1
PDF	https://arxiv.org/pdf/1906.05909v1.pdf
PWC	https://paperswithcode.com/paper/stand-alone-self-attention-in-vision-models
Repo
Framework