April 3, 2020

3310 words 16 mins read

Paper Group ANR 17

Paper Group ANR 17

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations. CompLex — A New Corpus for Lexical Complexity Predicition from Likert Scale Data. MEUZZ: Smart Seed Scheduling for Hybrid Fuzzing. Machine Learning for Network Slicing Resource Management: A Comprehensive Survey. Meshlet Priors for 3D Mesh Reconstructio …

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations

Title Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations
Authors John E. San Soucie, Heidi M. Sosik, Yogesh Girdhar
Abstract We propose a generative model for the spatio-temporal distribution of high dimensional categorical observations. These are commonly produced by robots equipped with an imaging sensor such as a camera, paired with an image classifier, potentially producing observations over thousands of categories. The proposed approach combines the use of Dirichlet distributions to model sparse co-occurrence relations between the observed categories using a latent variable, and Gaussian processes to model the latent variable’s spatio-temporal distribution. Experiments in this paper show that the resulting model is able to efficiently and accurately approximate the temporal distribution of high dimensional categorical measurements such as taxonomic observations of microscopic organisms in the ocean, even in unobserved (held out) locations, far from other samples. This work’s primary motivation is to enable deployment of informative path planning techniques over high dimensional categorical fields, which until now have been limited to scalar or low dimensional vector observations.
Tasks Gaussian Processes
Published 2020-03-26
URL https://arxiv.org/abs/2003.12120v1
PDF https://arxiv.org/pdf/2003.12120v1.pdf
PWC https://paperswithcode.com/paper/gaussian-dirichlet-random-fields-for

CompLex — A New Corpus for Lexical Complexity Predicition from Likert Scale Data

Title CompLex — A New Corpus for Lexical Complexity Predicition from Likert Scale Data
Authors Matthew Shardlow, Michael Cooper, Marcos Zampieri
Abstract Predicting which words are considered hard to understand for a given target population is a vital step in many NLP applications such as text simplification. This task is commonly referred to as Complex Word Identification (CWI). With a few exceptions, previous studies have approached the task as a binary classification task in which systems predict a complexity value (complex vs. non-complex) for a set of target words in a text. This choice is motivated by the fact that all CWI datasets compiled so far have been annotated using a binary annotation scheme. Our paper addresses this limitation by presenting the first English dataset for continuous lexical complexity prediction. We use a 5-point Likert scale scheme to annotate complex words in texts from three sources/domains: the Bible, Europarl, and biomedical texts. This resulted in a corpus of 9,476 sentences each annotated by around 7 annotators.
Tasks Complex Word Identification, Text Simplification
Published 2020-03-16
URL https://arxiv.org/abs/2003.07008v1
PDF https://arxiv.org/pdf/2003.07008v1.pdf
PWC https://paperswithcode.com/paper/complex-a-new-corpus-for-lexical-complexity

MEUZZ: Smart Seed Scheduling for Hybrid Fuzzing

Title MEUZZ: Smart Seed Scheduling for Hybrid Fuzzing
Authors Yaohui Chen, Mansour Ahmadi, Reza Mirzazade farkhani, Boyu Wang, Long Lu
Abstract Seed scheduling is a prominent factor in determining the yields of hybrid fuzzing. Existing hybrid fuzzers schedule seeds based on fixed heuristics that aim to predict input utilities. However, such heuristics are not generalizable as there exists no one-size-fits-all rule applicable to different programs. They may work well on the programs from which they were derived, but not others. To overcome this problem, we design a Machine learning-Enhanced hybrid fUZZing system (MEUZZ), which employs supervised machine learning for adaptive and generalizable seed scheduling. MEUZZ determines which new seeds are expected to produce better fuzzing yields based on the knowledge learned from past seed scheduling decisions made on the same or similar programs. MEUZZ’s learning is based on a series of features extracted via code reachability and dynamic analysis, which incurs negligible runtime overhead (in microseconds). Moreover, MEUZZ automatically infers the data labels by evaluating the fuzzing performance of each selected seed. As a result, MEUZZ is generally applicable to, and performs well on, various kinds of programs. Our evaluation shows MEUZZ significantly outperforms the state-of-the-art grey-box and hybrid fuzzers, achieving 27.1% more code coverage than QSYM. The learned models are reusable and transferable, which boosts fuzzing performance by 7.1% on average and improves 68% of the 56 cross-program fuzzing campaigns. MEUZZ discovered 47 deeply hidden and previously unknown bugs–with 21 confirmed and fixed by the developers–when fuzzing 8 well-tested programs with the same configurations as used in previous work.
Published 2020-02-20
URL https://arxiv.org/abs/2002.08568v1
PDF https://arxiv.org/pdf/2002.08568v1.pdf
PWC https://paperswithcode.com/paper/meuzz-smart-seed-scheduling-for-hybrid

Machine Learning for Network Slicing Resource Management: A Comprehensive Survey

Title Machine Learning for Network Slicing Resource Management: A Comprehensive Survey
Authors Bin Han, Hans D. Schotten
Abstract The emerging technology of multi-tenancy network slicing is considered as an essential feature of 5G cellular networks. It provides network slices as a new type of public cloud services, and therewith increases the service flexibility and enhances the network resource efficiency. Meanwhile, it raises new challenges of network resource management. A number of various methods have been proposed over the recent past years, in which machine learning and artificial intelligence techniques are widely deployed. In this article, we provide a survey to existing approaches of network slicing resource management, with a highlight on the roles played by machine learning in them.
Published 2020-01-22
URL https://arxiv.org/abs/2001.07974v1
PDF https://arxiv.org/pdf/2001.07974v1.pdf
PWC https://paperswithcode.com/paper/machine-learning-for-network-slicing-resource

Meshlet Priors for 3D Mesh Reconstruction

Title Meshlet Priors for 3D Mesh Reconstruction
Authors Abhishek Badki, Orazio Gallo, Jan Kautz, Pradeep Sen
Abstract Estimating a mesh from an unordered set of sparse, noisy 3D points is a challenging problem that requires carefully selected priors. Existing hand-crafted priors, such as smoothness regularizers, impose an undesirable trade-off between attenuating noise and preserving local detail. Recent deep-learning approaches produce impressive results by learning priors directly from the data. However, the priors are learned at the object level, which makes these algorithms class-specific, and even sensitive to the pose of the object. We introduce meshlets, small patches of mesh that we use to learn local shape priors. Meshlets act as a dictionary of local features and thus allow to use learned priors to reconstruct object meshes in any pose and from unseen classes, even when the noise is large and the samples sparse.
Published 2020-01-06
URL https://arxiv.org/abs/2001.01744v1
PDF https://arxiv.org/pdf/2001.01744v1.pdf
PWC https://paperswithcode.com/paper/meshlet-priors-for-3d-mesh-reconstruction

Two Decades of AI4NETS-AI/ML for Data Networks: Challenges & Research Directions

Title Two Decades of AI4NETS-AI/ML for Data Networks: Challenges & Research Directions
Authors Pedro Casas
Abstract The popularity of Artificial Intelligence (AI) – and of Machine Learning (ML) as an approach to AI, has dramatically increased in the last few years, due to its outstanding performance in various domains, notably in image, audio, and natural language processing. In these domains, AI success-stories are boosting the applied field. When it comes to AI/ML for data communication Networks (AI4NETS), and despite the many attempts to turn networks into learning agents, the successful application of AI/ML in networking is limited. There is a strong resistance against AI/ML-based solutions, and a striking gap between the extensive academic research and the actual deployments of such AI/ML-based systems in operational environments. The truth is, there are still many unsolved complex challenges associated to the analysis of networking data through AI/ML, which hinders its acceptability and adoption in the practice. In this positioning paper I elaborate on the most important show-stoppers in AI4NETS, and present a research agenda to tackle some of these challenges, enabling a natural adoption of AI/ML for networking. In particular, I focus the future research in AI4NETS around three major pillars: (i) to make AI/ML immediately applicable in networking problems through the concepts of effective learning, turning it into a useful and reliable way to deal with complex data-driven networking problems; (ii) to boost the adoption of AI/ML at the large scale by learning from the Internet-paradigm itself, conceiving novel distributed and hierarchical learning approaches mimicking the distributed topological principles and operation of the Internet itself; and (iii) to exploit the softwarization and distribution of networks to conceive AI/ML-defined Networks (AIDN), relying on the distributed generation and re-usage of knowledge through novel Knowledge Delivery Networks (KDNs).
Published 2020-03-03
URL https://arxiv.org/abs/2003.04080v1
PDF https://arxiv.org/pdf/2003.04080v1.pdf
PWC https://paperswithcode.com/paper/two-decades-of-ai4nets-aiml-for-data-networks

A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation

Title A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation
Authors Sheng Shi, Xinfeng Zhang, Wei Fan
Abstract Explainability is a gateway between Artificial Intelligence and society as the current popular deep learning models are generally weak in explaining the reasoning process and prediction results. Local Interpretable Model-agnostic Explanation (LIME) is a recent technique that explains the predictions of any classifier faithfully by learning an interpretable model locally around the prediction. However, the sampling operation in the standard implementation of LIME is defective. Perturbed samples are generated from a uniform distribution, ignoring the complicated correlation between features. This paper proposes a novel Modified Perturbed Sampling operation for LIME (MPS-LIME), which is formalized as the clique set construction problem. In image classification, MPS-LIME converts the superpixel image into an undirected graph. Various experiments show that the MPS-LIME explanation of the black-box model achieves much better performance in terms of understandability, fidelity, and efficiency.
Tasks Image Classification
Published 2020-02-18
URL https://arxiv.org/abs/2002.07434v1
PDF https://arxiv.org/pdf/2002.07434v1.pdf
PWC https://paperswithcode.com/paper/a-modified-perturbed-sampling-method-for

RPN: A Residual Pooling Network for Efficient Federated Learning

Title RPN: A Residual Pooling Network for Efficient Federated Learning
Authors Anbu Huang, Yuanyuan Chen, Yang Liu, Tianjian Chen, Qiang Yang
Abstract Federated learning is a new machine learning framework which enables different parties to collaboratively train a model while protecting data privacy and security. Due to model complexity, network unreliability and connection in-stability, communication cost has became a major bottleneck for applying federated learning to real-world applications. Current existing strategies are either need to manual setting for hyper-parameters, or break up the original process into multiple steps, which make it hard to realize end-to-end implementation. In this paper, we propose a novel compression strategy called Residual Pooling Network (RPN). Our experiments show that RPN not only reduce data transmission effectively, but also achieve almost the same performance as compared to standard federated learning. Our new approach performs as an end-to-end procedure, which should be readily applied to all CNN-based model training scenarios for improvement of communication efficiency, and hence make it easy to deploy in real-world application without human intervention.
Published 2020-01-23
URL https://arxiv.org/abs/2001.08600v1
PDF https://arxiv.org/pdf/2001.08600v1.pdf
PWC https://paperswithcode.com/paper/rpn-a-residual-pooling-network-for-efficient

Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent

Title Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
Authors Pu Zhao, Pin-Yu Chen, Siyue Wang, Xue Lin
Abstract Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability. Various adversarial attacks are proposed to sabotage the learning performance of DNN models. Among those, the black-box adversarial attack methods have received special attentions owing to their practicality and simplicity. Black-box attacks usually prefer less queries in order to maintain stealthy and low costs. However, most of the current black-box attack methods adopt the first-order gradient descent method, which may come with certain deficiencies such as relatively slow convergence and high sensitivity to hyper-parameter settings. In this paper, we propose a zeroth-order natural gradient descent (ZO-NGD) method to design the adversarial attacks, which incorporates the zeroth-order gradient estimation technique catering to the black-box attack scenario and the second-order natural gradient descent to achieve higher query efficiency. The empirical evaluations on image classification datasets demonstrate that ZO-NGD can obtain significantly lower model query complexities compared with state-of-the-art attack methods.
Tasks Adversarial Attack, Image Classification
Published 2020-02-18
URL https://arxiv.org/abs/2002.07891v1
PDF https://arxiv.org/pdf/2002.07891v1.pdf
PWC https://paperswithcode.com/paper/towards-query-efficient-black-box-adversary

MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification

Title MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification
Authors Yushi Lan, Yuan Liu, Maoqing Tian, Xinchi Zhou, Xuesen Zhang, Shuai Yi, Hongsheng Li
Abstract Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this paper, we propose MagnifierNet, a novel network which accurately mines details for each semantic region and selectively fuse all semantic feature representations. Apart from conventional global branch, our proposed network is composed of a Semantic Regularization Branch (SRB) as learning regularizer and a Semantic Fusion Branch (SFB) towards selectively semantic fusion. The SRB learns with limited number of semantic regions randomly sampled in each batch, which forces the network to learn detailed representation for each semantic region, and the SFB selectively fuses semantic region information in a sequential manner, focusing on beneficial information while neglecting irrelevant features or noises. In addition, we introduce a novel loss function “Semantic Diversity Loss” (SD Loss) to facilitate feature diversity and improves regularization among all semantic regions. State-of-the-art performance has been achieved on multiple datasets by large margins. Notably, we improve SOTA on CUHK03-Labeled Dataset by 12.6% in mAP and 8.9% in Rank-1. We also outperform existing works on CUHK03-Detected Dataset by 13.2% in mAP and 7.8% in Rank-1 respectively, which demonstrates the effectiveness of our method.
Tasks Person Re-Identification
Published 2020-02-25
URL https://arxiv.org/abs/2002.10979v2
PDF https://arxiv.org/pdf/2002.10979v2.pdf
PWC https://paperswithcode.com/paper/magnifiernet-towards-semantic-regularization

Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning

Title Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning
Authors Abhijeet Patil, Dipesh Tamboli, Swati Meena, Deepak Anand, Amit Sethi
Abstract Breast cancer has the highest mortality among cancers in women. Computer-aided pathology to analyze microscopic histopathology images for diagnosis with an increasing number of breast cancer patients can bring the cost and delays of diagnosis down. Deep learning in histopathology has attracted attention over the last decade of achieving state-of-the-art performance in classification and localization tasks. The convolutional neural network, a deep learning framework, provides remarkable results in tissue images analysis, but lacks in providing interpretation and reasoning behind the decisions. We aim to provide a better interpretation of classification results by providing localization on microscopic histopathology images. We frame the image classification problem as weakly supervised multiple instance learning problem where an image is collection of patches i.e. instances. Attention-based multiple instance learning (A-MIL) learns attention on the patches from the image to localize the malignant and normal regions in an image and use them to classify the image. We present classification and localization results on two publicly available BreakHIS and BACH dataset. The classification and visualization results are compared with other recent techniques. The proposed method achieves better localization results without compromising classification accuracy.
Tasks Image Classification, Multiple Instance Learning
Published 2020-02-16
URL https://arxiv.org/abs/2003.00823v1
PDF https://arxiv.org/pdf/2003.00823v1.pdf
PWC https://paperswithcode.com/paper/breast-cancer-histopathology-image

LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew

Title LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew
Authors Cyrus Rashtchian, Aneesh Sharma, David P. Woodruff
Abstract All-pairs set similarity is a widely used data mining task, even for large and high-dimensional datasets. Traditionally, similarity search has focused on discovering very similar pairs, for which a variety of efficient algorithms are known. However, recent work highlights the importance of finding pairs of sets with relatively small intersection sizes. For example, in a recommender system, two users may be alike even though their interests only overlap on a small percentage of items. In such systems, some dimensions are often highly skewed because they are very popular. Together these two properties render previous approaches infeasible for large input sizes. To address this problem, we present a new distributed algorithm, LSF-Join, for approximate all-pairs set similarity. The core of our algorithm is a randomized selection procedure based on Locality Sensitive Filtering. Our method deviates from prior approximate algorithms, which are based on Locality Sensitive Hashing. Theoretically, we show that LSF-Join efficiently finds most close pairs, even for small similarity thresholds and for skewed input sets. We prove guarantees on the communication, work, and maximum load of LSF-Join, and we also experimentally demonstrate its accuracy on multiple graphs.
Tasks Recommendation Systems
Published 2020-03-06
URL https://arxiv.org/abs/2003.02972v1
PDF https://arxiv.org/pdf/2003.02972v1.pdf
PWC https://paperswithcode.com/paper/lsf-join-locality-sensitive-filtering-for

Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective

Title Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective
Authors Min Gao, Junwei Zhang, Junliang Yu, Jundong Li, Junhao Wen, Qingyu Xiong
Abstract Recommender systems (RS) play a very important role in various aspects of people’s online life. Many companies leverage RS to help users discover new and favored items. Despite their empirical success, these systems still suffer from two main problems: data noise and data sparsity. In recent years, Generative Adversarial Networks (GANs) have received a surge of interests in many fields because of their great potential to learn complex real data distribution, and they also provide new means to mitigate the aforementioned problems of RS. Particularly, owing to adversarial learning, the problem of data noise can be handled by adding adversarial perturbations or forcing discriminators to tell the informative and uninformative data examples apart. As for the mitigation of data sparsity issue, the GAN-based models are able to replicate the real distribution of the user-item interactions and augment the available data. To gain a comprehensive understanding of these GAN-based recommendation models, we provide a retrospective of these studies and organize them from a problem-driven perspective. Specifically, we propose a taxonomy of these models, along with a detailed description of them and their advantages. Finally, we elaborate on several open issues and expand on current trends in the GAN-based RS.
Tasks Recommendation Systems
Published 2020-03-05
URL https://arxiv.org/abs/2003.02474v1
PDF https://arxiv.org/pdf/2003.02474v1.pdf
PWC https://paperswithcode.com/paper/recommender-systems-based-on-generative

Semi-supervised Learning Meets Factorization: Learning to Recommend with Chain Graph Model

Title Semi-supervised Learning Meets Factorization: Learning to Recommend with Chain Graph Model
Authors Chaochao Chen, Kevin C. Chang, Qibing Li, Xiaolin Zheng
Abstract Recently latent factor model (LFM) has been drawing much attention in recommender systems due to its good performance and scalability. However, existing LFMs predict missing values in a user-item rating matrix only based on the known ones, and thus the sparsity of the rating matrix always limits their performance. Meanwhile, semi-supervised learning (SSL) provides an effective way to alleviate the label (i.e., rating) sparsity problem by performing label propagation, which is mainly based on the smoothness insight on affinity graphs. However, graph-based SSL suffers serious scalability and graph unreliable problems when directly being applied to do recommendation. In this paper, we propose a novel probabilistic chain graph model (CGM) to marry SSL with LFM. The proposed CGM is a combination of Bayesian network and Markov random field. The Bayesian network is used to model the rating generation and regression procedures, and the Markov random field is used to model the confidence-aware smoothness constraint between the generated ratings. Experimental results show that our proposed CGM significantly outperforms the state-of-the-art approaches in terms of four evaluation metrics, and with a larger performance margin when data sparsity increases.
Tasks Recommendation Systems
Published 2020-03-05
URL https://arxiv.org/abs/2003.02452v1
PDF https://arxiv.org/pdf/2003.02452v1.pdf
PWC https://paperswithcode.com/paper/semi-supervised-learning-meets-factorization

Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision

Title Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision
Authors Xuan Wang, Xiangchen Song, Yingjun Guan, Bangzheng Li, Jiawei Han
Abstract We created this CORD-19-NER dataset with comprehensive named entity recognition (NER) on the COVID-19 Open Research Dataset Challenge (CORD-19) corpus (2020- 03-13). This CORD-19-NER dataset covers 74 fine-grained named entity types. It is automatically generated by combining the annotation results from four sources: (1) pre-trained NER model on 18 general entity types from Spacy, (2) pre-trained NER model on 18 biomedical entity types from SciSpacy, (3) knowledge base (KB)-guided NER model on 127 biomedical entity types with our distantly-supervised NER method, and (4) seed-guided NER model on 8 new entity types (specifically related to the COVID-19 studies) with our weakly-supervised NER method. We hope this dataset can help the text mining community build downstream applications. We also hope this dataset can bring insights for the COVID- 19 studies, both on the biomedical side and on the social side.
Tasks Named Entity Recognition
Published 2020-03-27
URL https://arxiv.org/abs/2003.12218v2
PDF https://arxiv.org/pdf/2003.12218v2.pdf
PWC https://paperswithcode.com/paper/comprehensive-named-entity-recognition-on
comments powered by Disqus