January 27, 2020

3270 words 16 mins read

Paper Group ANR 1178

Knowledge Authoring and Question Answering with KALM. Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving. SCE: A manifold regularized set-covering method for data partitioning. BUT System Description to VoxCeleb Speaker Recognition Challenge 2019. Small Target Detection for Search and Rescue Operations using Distributed …

Knowledge Authoring and Question Answering with KALM


Title	Knowledge Authoring and Question Answering with KALM
Authors	Tiantian Gao
Abstract	Knowledge representation and reasoning (KRR) is one of the key areas in artificial intelligence (AI) field. It is intended to represent the world knowledge in formal languages (e.g., Prolog, SPARQL) and then enhance the expert systems to perform querying and inference tasks. Currently, constructing large scale knowledge bases (KBs) with high quality is prohibited by the fact that the construction process requires many qualified knowledge engineers who not only understand the domain-specific knowledge but also have sufficient skills in knowledge representation. Unfortunately, qualified knowledge engineers are in short supply. Therefore, it would be very useful to build a tool that allows the user to construct and query the KB simply via text. Although there is a number of systems developed for knowledge extraction and question answering, they mainly fail in that these system don’t achieve high enough accuracy whereas KRR is highly sensitive to erroneous data. In this thesis proposal, I will present Knowledge Authoring Logic Machine (KALM), a rule-based system which allows the user to author knowledge and query the KB in text. The experimental results show that KALM achieved superior accuracy in knowledge authoring and question answering as compared to the state-of-the-art systems.
Tasks	Question Answering
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00840v3
PDF	https://arxiv.org/pdf/1905.00840v3.pdf
PWC	https://paperswithcode.com/paper/kalm-a-rule-based-approach-for-knowledge
Repo
Framework

Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving


Title	Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
Authors	Rulin Shao, Hongyu He, Hui Liu, Dianbo Liu
Abstract	Artificial neural network has achieved unprecedented success in the medical domain. This success depends on the availability of massive and representative datasets. However, data collection is often prevented by privacy concerns and people want to take control over their sensitive information during both training and using processes. To address this problem, we propose a privacy-preserving method for the distributed system, Stochastic Channel-Based Federated Learning (SCBF), which enables the participants to train a high-performance model cooperatively without sharing their inputs. Specifically, we design, implement and evaluate a channel-based update algorithm for the central server in a distributed system, which selects the channels with regard to the most active features in a training loop and uploads them as learned information from local datasets. A pruning process is applied to the algorithm based on the validation set, which serves as a model accelerator. In the experiment, our model presents better performances and higher saturating speed than the Federated Averaging method which reveals all the parameters of local models to the server when updating. We also demonstrate that the saturating rate of performance could be promoted by introducing a pruning process. And further improvement could be achieved by tuning the pruning rate. Our experiment shows that 57% of the time is saved by the pruning process with only a reduction of 0.0047 in AUCROC performance and a reduction of 0.0068 in AUCPR.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.11160v3
PDF	https://arxiv.org/pdf/1910.11160v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-channel-based-federated-learning
Repo
Framework

SCE: A manifold regularized set-covering method for data partitioning


Title	SCE: A manifold regularized set-covering method for data partitioning
Authors	Xuelong Li, Quanmao Lu, Yongsheng Dong, Dacheng Tao
Abstract	Cluster analysis plays a very important role in data analysis. In these years, cluster ensemble, as a cluster analysis tool, has drawn much attention for its robustness, stability, and accuracy. Many efforts have been done to combine different initial clustering results into a single clustering solution with better performance. However, they neglect the structure information of the raw data in performing the cluster ensemble. In this paper, we propose a Structural Cluster Ensemble (SCE) algorithm for data partitioning formulated as a set-covering problem. In particular, we construct a Laplacian regularized objective function to capture the structure information among clusters. Moreover, considering the importance of the discriminative information underlying in the initial clustering results, we add a discriminative constraint into our proposed objective function. Finally, we verify the performance of the SCE algorithm on both synthetic and real data sets. The experimental results show the effectiveness of our proposed method SCE algorithm.
Tasks
Published	2019-04-17
URL	http://arxiv.org/abs/1904.08412v1
PDF	http://arxiv.org/pdf/1904.08412v1.pdf
PWC	https://paperswithcode.com/paper/sce-a-manifold-regularized-set-covering
Repo
Framework

BUT System Description to VoxCeleb Speaker Recognition Challenge 2019


Title	BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
Authors	Hossein Zeinali, Shuai Wang, Anna Silnova, Pavel Matějka, Oldřich Plchot
Abstract	In this report, we describe the submission of Brno University of Technology (BUT) team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2019. We also provide a brief analysis of different systems on VoxCeleb-1 test sets. Submitted systems for both Fixed and Open conditions are a fusion of 4 Convolutional Neural Network (CNN) topologies. The first and second networks have ResNet34 topology and use two-dimensional CNNs. The last two networks are one-dimensional CNN and are based on the x-vector extraction topology. Some of the networks are fine-tuned using additive margin angular softmax. Kaldi FBanks and Kaldi PLPs were used as features. The difference between Fixed and Open systems lies in the used training data and fusion strategy. The best systems for Fixed and Open conditions achieved 1.42% and 1.26% ERR on the challenge evaluation set respectively.
Tasks	Speaker Recognition
Published	2019-10-16
URL	https://arxiv.org/abs/1910.12592v1
PDF	https://arxiv.org/pdf/1910.12592v1.pdf
PWC	https://paperswithcode.com/paper/but-system-description-to-voxceleb-speaker
Repo
Framework

Small Target Detection for Search and Rescue Operations using Distributed Deep Learning and Synthetic Data Generation


Title	Small Target Detection for Search and Rescue Operations using Distributed Deep Learning and Synthetic Data Generation
Authors	Kyongsik Yun, Luan Nguyen, Tuan Nguyen, Doyoung Kim, Sarah Eldin, Alexander Huyen, Thomas Lu, Edward Chow
Abstract	It is important to find the target as soon as possible for search and rescue operations. Surveillance camera systems and unmanned aerial vehicles (UAVs) are used to support search and rescue. Automatic object detection is important because a person cannot monitor multiple surveillance screens simultaneously for 24 hours. Also, the object is often too small to be recognized by the human eye on the surveillance screen. This study used UAVs around the Port of Houston and fixed surveillance cameras to build an automatic target detection system that supports the US Coast Guard (USCG) to help find targets (e.g., person overboard). We combined image segmentation, enhancement, and convolution neural networks to reduce detection time to detect small targets. We compared the performance between the auto-detection system and the human eye. Our system detected the target within 8 seconds, but the human eye detected the target within 25 seconds. Our systems also used synthetic data generation and data augmentation techniques to improve target detection accuracy. This solution may help the search and rescue operations of the first responders in a timely manner.
Tasks	Data Augmentation, Object Detection, Semantic Segmentation, Synthetic Data Generation
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11619v1
PDF	http://arxiv.org/pdf/1904.11619v1.pdf
PWC	https://paperswithcode.com/paper/small-target-detection-for-search-and-rescue
Repo
Framework

MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression


Title	MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
Authors	Jie Zhang, Xiaolong Wang, Dawei Li, Shalini Ghosh, Abhishek Kolagunda, Yalin Wang
Abstract	State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer. However, they process each hidden layer individually while neglecting the common components across layers, and thus are not able to fully exploit the potential redundancy space for compression. To solve the above problem and enable further compression of a model, removing the cross-layer redundancy and mining the layer-wise inheritance knowledge is necessary. In this paper, we introduce a holistic model compression framework, namely MIning Cross-layer Inherent similarity Knowledge (MICIK), to fully excavate the potential redundancy space. The proposed MICIK framework simultaneously, (1) learns the common and unique weight components across deep neural network layers to increase compression rate; (2) preserves the inherent similarity knowledge of nearby layers and distant layers to minimize the accuracy loss and (3) can be complementary to other existing compression techniques such as knowledge distillation. Extensive experiments on large-scale convolutional neural networks demonstrate that MICIK is superior over state-of-the-art model compression approaches with 16X parameter reduction on VGG-16 and 6X on GoogLeNet, all without accuracy loss.
Tasks	Model Compression
Published	2019-02-03
URL	http://arxiv.org/abs/1902.00918v1
PDF	http://arxiv.org/pdf/1902.00918v1.pdf
PWC	https://paperswithcode.com/paper/micik-mining-cross-layer-inherent-similarity
Repo
Framework

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images


Title	DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images
Authors	Haris Cheong, Sripad Krishna Devalla, Tan Hung Pham, Zhang Liang, Tin Aung Tun, Xiaofei Wang, Shamira Perera, Leopold Schmetterer, Aung Tin, Craig Boote, Alexandre H. Thiery, Michael J. A. Girard
Abstract	Purpose: To remove retinal shadows from optical coherence tomography (OCT) images of the optic nerve head(ONH). Methods:2328 OCT images acquired through the center of the ONH using a Spectralis OCT machine for both eyes of 13 subjects were used to train a generative adversarial network (GAN) using a custom loss function. Image quality was assessed qualitatively (for artifacts) and quantitatively using the intralayer contrast: a measure of shadow visibility ranging from 0 (shadow-free) to 1 (strong shadow) and compared to compensated images. This was computed in the Retinal Nerve Fiber Layer (RNFL), the Inner Plexiform Layer (IPL), the Photoreceptor layer (PR) and the Retinal Pigment Epithelium (RPE) layers. Results: Output images had improved intralayer contrast in all ONH tissue layers. On average the intralayer contrast decreased by 33.7$\pm$6.81%, 28.8$\pm$10.4%, 35.9$\pm$13.0%, and43.0$\pm$19.5%for the RNFL, IPL, PR, and RPE layers respectively, indicating successful shadow removal across all depths. This compared to 70.3$\pm$22.7%, 33.9$\pm$11.5%, 47.0$\pm$11.2%, 26.7$\pm$19.0%for compensation. Output images were also free from artifacts commonly observed with compensation. Conclusions: DeshadowGAN significantly corrected blood vessel shadows in OCT images of the ONH. Our algorithm may be considered as a pre-processing step to improve the performance of a wide range of algorithms including those currently being used for OCT image segmentation, denoising, and classification. Translational Relevance: DeshadowGAN could be integrated to existing OCT devices to improve the diagnosis and prognosis of ocular pathologies.
Tasks	Denoising, Semantic Segmentation
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02844v1
PDF	https://arxiv.org/pdf/1910.02844v1.pdf
PWC	https://paperswithcode.com/paper/deshadowgan-a-deep-learning-approach-to
Repo
Framework

Human and Automatic Detection of Generated Text


Title	Human and Automatic Detection of Generated Text
Authors	Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch, Douglas Eck
Abstract	With the advent of generative models with a billion parameters or more, it is now possible to automatically generate vast amounts of human-sounding text. This raises questions into just how human-like is the machine-generated text, and how long does a text excerpt need to be for both humans and automatic discriminators to be able reliably detect that it was machine-generated. In this paper, we conduct a thorough investigation of how choices such as sampling strategy and text excerpt length can impact the performance of automatic detection methods as well as human raters. We find that the sampling strategies which result in more human-like text according to human raters create distributional differences from human-written text that make detection easy for automatic discriminators.
Tasks
Published	2019-11-02
URL	https://arxiv.org/abs/1911.00650v1
PDF	https://arxiv.org/pdf/1911.00650v1.pdf
PWC	https://paperswithcode.com/paper/human-and-automatic-detection-of-generated
Repo
Framework

Multitask Learning for Network Traffic Classification


Title	Multitask Learning for Network Traffic Classification
Authors	Shahbaz Rezaei, Xin Liu
Abstract	Traffic classification has various applications in today’s Internet, from resource allocation, billing and QoS purposes in ISPs to firewall and malware detection in clients. Classical machine learning algorithms and deep learning models have been widely used to solve the traffic classification task. However, training such models requires a large amount of labeled data. Labeling data is often the most difficult and time-consuming process in building a classifier. To solve this challenge, we reformulate the traffic classification into a multi-task learning framework where bandwidth requirement and duration of a flow are predicted along with the traffic class. The motivation of this approach is twofold: First, bandwidth requirement and duration are useful in many applications, including routing, resource allocation, and QoS provisioning. Second, these two values can be obtained from each flow easily without the need for human labeling or capturing flows in a controlled and isolated environment. We show that with a large amount of easily obtainable data samples for bandwidth and duration prediction tasks, and only a few data samples for the traffic classification task, one can achieve high accuracy. We conduct two experiment with ISCX and QUIC public datasets and show the efficacy of our approach.
Tasks	Malware Detection, Multi-Task Learning
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05248v1
PDF	https://arxiv.org/pdf/1906.05248v1.pdf
PWC	https://paperswithcode.com/paper/multitask-learning-for-network-traffic
Repo
Framework

Probing the State of the Art: A Critical Look at Visual Representation Evaluation


Title	Probing the State of the Art: A Critical Look at Visual Representation Evaluation
Authors	Cinjon Resnick, Zeping Zhan, Joan Bruna
Abstract	Self-supervised research improved greatly over the past half decade, with much of the growth being driven by objectives that are hard to quantitatively compare. These techniques include colorization, cyclical consistency, and noise-contrastive estimation from image patches. Consequently, the field has settled on a handful of measurements that depend on linear probes to adjudicate which approaches are the best. Our first contribution is to show that this test is insufficient and that models which perform poorly (strongly) on linear classification can perform strongly (weakly) on more involved tasks like temporal activity localization. Our second contribution is to analyze the capabilities of five different representations. And our third contribution is a much needed new dataset for temporal activity localization.
Tasks	Colorization
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00215v1
PDF	https://arxiv.org/pdf/1912.00215v1.pdf
PWC	https://paperswithcode.com/paper/probing-the-state-of-the-art-a-critical-look
Repo
Framework

Self-Attentive Hawkes Processes


Title	Self-Attentive Hawkes Processes
Authors	Qiang Zhang, Aldo Lipani, Omer Kirnap, Emine Yilmaz
Abstract	Asynchronous events on the continuous time domain, e.g., social media actions and stock transactions, occur frequently in the world. The ability to recognize occurrence patterns of event sequences is crucial to predict which typeof events will happen next and when. A de facto standard mathematical framework to do this is the Hawkes process. In order to enhance expressivity of multivariate Hawkes processes, conventional statistical methods and deep recurrent networks have been employed to modify its intensity function. The former is highly interpretable and requires small size of training data but relies on correct model design while the latter has less dependency on prior knowledge and is more powerful in capturing complicated patterns. We leverage pros and cons of these models and propose a self-attentive Hawkes process(SAHP). The proposed method adapts self-attention to fit the intensity function of Hawkes processes. This design has two benefits:(1) compared with conventional statistical methods, the SAHP is more powerful to identify complicated dependency relationships between temporal events; (2)compared with deep recurrent networks, the self-attention mechanism is able to capture longer historical information, and is more interpretable because the learnt attention weight tensor shows contributions of each historical event. Experiments on four real-world datasets demonstrate the effectiveness of the proposed method.
Tasks
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07561v2
PDF	https://arxiv.org/pdf/1907.07561v2.pdf
PWC	https://paperswithcode.com/paper/self-attentive-hawkes-processes
Repo
Framework

Fast Haar Transforms for Graph Neural Networks


Title	Fast Haar Transforms for Graph Neural Networks
Authors	Ming Li, Zheng Ma, Yu Guang Wang, Xiaosheng Zhuang
Abstract	Graph Neural Networks (GNNs) have become a topic of intense research recently due to their powerful capability in high-dimensional classification and regression tasks for graph-structured data. However, as GNNs typically define the graph convolution by the orthonormal basis for the graph Laplacian, they suffer from high computational cost when the graph size is large. This paper introduces Haar basis which is a sparse and localized orthonormal system for a coarse-grained chain on graph. The graph convolution under Haar basis, called Haar convolution, can be defined accordingly for GNNs. The sparsity and locality of the Haar basis allow Fast Haar Transforms (FHTs) on graph, by which a fast evaluation of Haar convolution between graph data and filters can be achieved. We conduct experiments on GNNs equipped with Haar convolution, which demonstrates state-of-the-art results on graph-based regression and node classification tasks.
Tasks	Node Classification
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04786v3
PDF	https://arxiv.org/pdf/1907.04786v3.pdf
PWC	https://paperswithcode.com/paper/haar-transforms-for-graph-neural-networks
Repo
Framework

Dimensional Reweighting Graph Convolutional Networks


Title	Dimensional Reweighting Graph Convolutional Networks
Authors	Xu Zou, Qiuye Jia, Jianwei Zhang, Chang Zhou, Hongxia Yang, Jie Tang
Abstract	Graph Convolution Networks (GCNs) are becoming more and more popular for learning node representations on graphs. Though there exist various developments on sampling and aggregation to accelerate the training process and improve the performances, limited works focus on dealing with the dimensional information imbalance of node representations. To bridge the gap, we propose a method named Dimensional reweighting Graph Convolution Network (DrGCN). We theoretically prove that our DrGCN can guarantee to improve the stability of GCNs via mean field theory. Our dimensional reweighting method is very flexible and can be easily combined with most sampling and aggregation techniques for GCNs. Experimental results demonstrate its superior performances on several challenging transductive and inductive node classification benchmark datasets. Our DrGCN also outperforms existing models on an industrial-sized Alibaba recommendation dataset.
Tasks	Node Classification
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02237v2
PDF	https://arxiv.org/pdf/1907.02237v2.pdf
PWC	https://paperswithcode.com/paper/dimensional-reweighting-graph-convolutional
Repo
Framework

Challenges for an Ontology of Artificial Intelligence


Title	Challenges for an Ontology of Artificial Intelligence
Authors	Scott H. Hawley
Abstract	Of primary importance in formulating a response to the increasing prevalence and power of artificial intelligence (AI) applications in society are questions of ontology. Questions such as: What “are” these systems? How are they to be regarded? How does an algorithm come to be regarded as an agent? We discuss three factors which hinder discussion and obscure attempts to form a clear ontology of AI: (1) the various and evolving definitions of AI, (2) the tendency for pre-existing technologies to be assimilated and regarded as “normal,” and (3) the tendency of human beings to anthropomorphize. This list is not intended as exhaustive, nor is it seen to preclude entirely a clear ontology, however, these challenges are a necessary set of topics for consideration. Each of these factors is seen to present a ‘moving target’ for discussion, which poses a challenge for both technical specialists and non-practitioners of AI systems development (e.g., philosophers and theologians) to speak meaningfully given that the corpus of AI structures and capabilities evolves at a rapid pace. Finally, we present avenues for moving forward, including opportunities for collaborative synthesis for scholars in philosophy and science.
Tasks
Published	2019-02-25
URL	http://arxiv.org/abs/1903.03171v1
PDF	http://arxiv.org/pdf/1903.03171v1.pdf
PWC	https://paperswithcode.com/paper/challenges-for-an-ontology-of-artificial
Repo
Framework

Is ‘Unsupervised Learning’ a Misconceived Term?


Title	Is ‘Unsupervised Learning’ a Misconceived Term?
Authors	Stephen G. Odaibo
Abstract	Is all of machine learning supervised to some degree? The field of machine learning has traditionally been categorized pedagogically into $supervised~vs~unsupervised~learning$; where supervised learning has typically referred to learning from labeled data, while unsupervised learning has typically referred to learning from unlabeled data. In this paper, we assert that all machine learning is in fact supervised to some degree, and that the scope of supervision is necessarily commensurate to the scope of learning potential. In particular, we argue that clustering algorithms such as k-means, and dimensionality reduction algorithms such as principal component analysis, variational autoencoders, and deep belief networks are each internally supervised by the data itself to learn their respective representations of its features. Furthermore, these algorithms are not capable of external inference until their respective outputs (clusters, principal components, or representation codes) have been identified and externally labeled in effect. As such, they do not suffice as examples of unsupervised learning. We propose that the categorization `supervised vs unsupervised learning’ be dispensed with, and instead, learning algorithms be categorized as either $internally~or~externally~supervised$ (or both). We believe this change in perspective will yield new fundamental insights into the structure and character of data and of learning algorithms. \|
Tasks	Dimensionality Reduction
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03259v1
PDF	http://arxiv.org/pdf/1904.03259v1.pdf
PWC	https://paperswithcode.com/paper/is-unsupervised-learning-a-misconceived-term
Repo
Framework