January 26, 2020

3388 words 16 mins read

Paper Group ANR 1459

DeepCloud. The Application of a Data-driven, Generative Model in Design. Order Acceptance and Scheduling with Sequence-dependent Setup Times: a New Memetic Algorithm and Benchmark of the State of the Art. PEA265: Perceptual Assessment of Video Compression Artifacts. Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Rea …

DeepCloud. The Application of a Data-driven, Generative Model in Design


Title	DeepCloud. The Application of a Data-driven, Generative Model in Design
Authors	Ardavan Bidgoli, Pedro Veloso
Abstract	Generative systems have a significant potential to synthesize innovative design alternatives. Still, most of the common systems that have been adopted in design require the designer to explicitly define the specifications of the procedures and in some cases the design space. In contrast, a generative system could potentially learn both aspects through processing a database of existing solutions without the supervision of the designer. To explore this possibility, we review recent advancements of generative models in machine learning and current applications of learning techniques in design. Then, we describe the development of a data-driven generative system titled DeepCloud. It combines an autoencoder architecture for point clouds with a web-based interface and analog input devices to provide an intuitive experience for data-driven generation of design alternatives. We delineate the implementation of two prototypes of DeepCloud, their contributions, and potentials for generative design.
Tasks
Published	2019-04-01
URL	http://arxiv.org/abs/1904.01083v1
PDF	http://arxiv.org/pdf/1904.01083v1.pdf
PWC	https://paperswithcode.com/paper/deepcloud-the-application-of-a-data-driven
Repo
Framework

Order Acceptance and Scheduling with Sequence-dependent Setup Times: a New Memetic Algorithm and Benchmark of the State of the Art


Title	Order Acceptance and Scheduling with Sequence-dependent Setup Times: a New Memetic Algorithm and Benchmark of the State of the Art
Authors	Lei He, Arthur Guijt, Mathijs de Weerdt, Lining Xing, Neil Yorke-Smith
Abstract	The Order Acceptance and Scheduling (OAS) problem describes a class of real-world problems such as in smart manufacturing and satellite scheduling. This problem consists of simultaneously selecting a subset of orders to be processed as well as determining the associated schedule. A common generalization includes sequence-dependent setup times and time windows. A novel memetic algorithm for this problem, called Sparrow, comprises a hybridization of biased random key genetic algorithm (BRKGA) and adaptive large neighbourhood search (ALNS). Sparrow integrates the exploration ability of BRKGA and the exploitation ability of ALNS. On a set of standard benchmark instances, this algorithm obtains better-quality solutions with runtimes comparable to state-of-the-art algorithms. To further understand the strengths and weaknesses of these algorithms, their performance is also compared on a set of new benchmark instances with more realistic properties. We conclude that Sparrow is distinguished by its ability to solve difficult instances from the OAS literature, and that the hybrid steady-state genetic algorithm (HSSGA) performs well on large instances in terms of optimality gap, although taking more time than Sparrow.
Tasks
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01982v1
PDF	https://arxiv.org/pdf/1910.01982v1.pdf
PWC	https://paperswithcode.com/paper/order-acceptance-and-scheduling-with-sequence
Repo
Framework

PEA265: Perceptual Assessment of Video Compression Artifacts


Title	PEA265: Perceptual Assessment of Video Compression Artifacts
Authors	Liqun Lin, Shiqi Yu, Tiesong Zhao, Member, IEEE, Zhou Wang, Fellow, IEEE
Abstract	The most widely used video encoders share a common hybrid coding framework that includes block-based motion estimation/compensation and block-based transform coding. Despite their high coding efficiency, the encoded videos often exhibit visually annoying artifacts, denoted as Perceivable Encoding Artifacts (PEAs), which significantly degrade the visual Qualityof- Experience (QoE) of end users. To monitor and improve visual QoE, it is crucial to develop subjective and objective measures that can identify and quantify various types of PEAs. In this work, we make the first attempt to build a large-scale subjectlabelled database composed of H.265/HEVC compressed videos containing various PEAs. The database, namely the PEA265 database, includes 4 types of spatial PEAs (i.e. blurring, blocking, ringing and color bleeding) and 2 types of temporal PEAs (i.e. flickering and floating). Each containing at least 60,000 image or video patches with positive and negative labels. To objectively identify these PEAs, we train Convolutional Neural Networks (CNNs) using the PEA265 database. It appears that state-of-theart ResNeXt is capable of identifying each type of PEAs with high accuracy. Furthermore, we define PEA pattern and PEA intensity measures to quantify PEA levels of compressed video sequence. We believe that the PEA265 database and our findings will benefit the future development of video quality assessment methods and perceptually motivated video encoders.
Tasks	Motion Estimation, Video Compression, Video Quality Assessment
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00473v1
PDF	http://arxiv.org/pdf/1903.00473v1.pdf
PWC	https://paperswithcode.com/paper/pea265-perceptual-assessment-of-video
Repo
Framework

Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning


Title	Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning
Authors	Andrea Galassi, Kristian Kersting, Marco Lippi, Xiaoting Shao, Paolo Torroni
Abstract	Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap toward performing advanced reasoning tasks. In this position paper, we posit that neural-symbolic and statistical relational learning could play a crucial role in the integration of symbolic and sub-symbolic methods to achieve this goal.
Tasks	Relational Reasoning
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09103v3
PDF	https://arxiv.org/pdf/1905.09103v3.pdf
PWC	https://paperswithcode.com/paper/neural-symbolic-argumentation-mining-an
Repo
Framework

Reduced-order modeling using Dynamic Mode Decomposition and Least Angle Regression


Title	Reduced-order modeling using Dynamic Mode Decomposition and Least Angle Regression
Authors	John Graff, Xianzhang Xu, Francis D. Lagor, Tarunraj Singh
Abstract	Dynamic Mode Decomposition (DMD) yields a linear, approximate model of a system’s dynamics that is built from data. We seek to reduce the order of this model by identifying a reduced set of modes that best fit the output. We adopt a model selection algorithm from statistics and machine learning known as Least Angle Regression (LARS). We modify LARS to be complex-valued and utilize LARS to select DMD modes. We refer to the resulting algorithm as Least Angle Regression for Dynamic Mode Decomposition (LARS4DMD). Sparsity-Promoting Dynamic Mode Decomposition (DMDSP), a popular mode-selection algorithm, serves as a benchmark for comparison. Numerical results from a Poiseuille flow test problem show that LARS4DMD yields reduced-order models that have comparable performance to DMDSP. LARS4DMD has the added benefit that the regularization weighting parameter required for DMDSP is not needed.
Tasks	Model Selection
Published	2019-05-16
URL	https://arxiv.org/abs/1905.07027v2
PDF	https://arxiv.org/pdf/1905.07027v2.pdf
PWC	https://paperswithcode.com/paper/reduced-order-modeling-using-dynamic-mode
Repo
Framework

Test Selection for Deep Learning Systems


Title	Test Selection for Deep Learning Systems
Authors	Wei Ma, Mike Papadakis, Anestis Tsakmalis, Maxime Cordy, Yves Le Traon
Abstract	Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can automatically select candidate test data to test deep learning models. Recent research has focused on adapting test selection metrics from code-based software testing (such as coverage) to deep learning. However, deep learning models have different attributes from code such as spread of computations across the entire network reflecting training data properties, balance of neuron weights and redundancy (use of many more neurons than needed). Such differences make code-based metrics inappropriate to select data that can challenge the models (can trigger misclassification). We thus propose a set of test selection metrics based on the notion of model uncertainty (model confidence on specific inputs). Intuitively, the more uncertain we are about a candidate sample, the more likely it is that this sample triggers a misclassification. Similarly, the samples for which we are the most uncertain, are the most informative and should be used to improve the model by retraining. We evaluate these metrics on two widely-used image classification problems involving real and artificial (adversarial) data. We show that uncertainty-based metrics have a strong ability to select data that are misclassified and lead to major improvement in classification accuracy during retraining: up to 80% more gain than random selection and other state-of-the-art metrics on one dataset and up to 29% on the other.
Tasks	Image Classification
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13195v1
PDF	http://arxiv.org/pdf/1904.13195v1.pdf
PWC	https://paperswithcode.com/paper/test-selection-for-deep-learning-systems
Repo
Framework

Encoding word order in complex embeddings


Title	Encoding word order in complex embeddings
Authors	Benyou Wang, Donghao Zhao, Christina Lioma, Qiuchi Li, Peng Zhang, Jakob Grue Simonsen
Abstract	Sequential word order is important when processing text. Currently, neural networks (NNs) address this by modeling word position using position embeddings. The problem is that position embeddings capture the position of individual words, but not the ordered relationship (e.g., adjacency or precedence) between individual word positions. We present a novel and principled solution for modeling both the global absolute positions of words and their order relationships. Our solution generalizes word embeddings, previously defined as independent vectors, to continuous word functions over a variable (position). The benefit of continuous functions over variable positions is that word representations shift smoothly with increasing positions. Hence, word representations in different positions can correlate with each other in a continuous function. The general solution of these functions is extended to complex-valued domain due to richer representations. We extend CNN, RNN and Transformer NNs to complex-valued versions to incorporate our complex embedding (we make all code available). Experiments on text classification, machine translation and language modeling show gains over both classical word embeddings and position-enriched word embeddings. To our knowledge, this is the first work in NLP to link imaginary numbers in complex-valued representations to concrete meanings (i.e., word order).
Tasks	Language Modelling, Machine Translation, Text Classification, Word Embeddings
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12333v1
PDF	https://arxiv.org/pdf/1912.12333v1.pdf
PWC	https://paperswithcode.com/paper/encoding-word-order-in-complex-embeddings-1
Repo
Framework

A Comparison Study on Nonlinear Dimension Reduction Methods with Kernel Variations: Visualization, Optimization and Classification


Title	A Comparison Study on Nonlinear Dimension Reduction Methods with Kernel Variations: Visualization, Optimization and Classification
Authors	Katherine C. Kempfert, Yishi Wang, Cuixian Chen, Samuel W. K. Wong
Abstract	Because of high dimensionality, correlation among covariates, and noise contained in data, dimension reduction (DR) techniques are often employed to the application of machine learning algorithms. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and their kernel variants (KPCA, KLDA) are among the most popular DR methods. Recently, Supervised Kernel Principal Component Analysis (SKPCA) has been shown as another successful alternative. In this paper, brief reviews of these popular techniques are presented first. We then conduct a comparative performance study based on three simulated datasets, after which the performance of the techniques are evaluated through application to a pattern recognition problem in face image analysis. The gender classification problem is considered on MORPH-II and FG-NET, two popular longitudinal face aging databases. Several feature extraction methods are used, including biologically-inspired features (BIF), local binary patterns (LBP), histogram of oriented gradients (HOG), and the Active Appearance Model (AAM). After applications of DR methods, a linear support vector machine (SVM) is deployed with gender classification accuracy rates exceeding 95% on MORPH-II, competitive with benchmark results. A parallel computational approach is also proposed, attaining faster processing speeds and similar recognition rates on MORPH-II. Our computational approach can be applied to practical gender classification systems and generalized to other face analysis tasks, such as race classification and age prediction.
Tasks	Dimensionality Reduction
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02114v1
PDF	https://arxiv.org/pdf/1910.02114v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-study-on-nonlinear-dimension
Repo
Framework

Reinforcement Learning with Non-Markovian Rewards


Title	Reinforcement Learning with Non-Markovian Rewards
Authors	Maor Gaon, Ronen I. Brafman
Abstract	The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing coffee only if requested earlier and not yet served, is non-Markovian if the state only records current requests and deliveries. Past work considered the problem of modeling and solving MDPs with non-Markovian rewards (NMR), but we know of no principled approaches for RL with NMR. Here, we address the problem of policy learning from experience with such rewards. We describe and evaluate empirically four combinations of the classical RL algorithm Q-learning and R-max with automata learning algorithms to obtain new RL algorithms for domains with NMR. We also prove that some of these variants converge to an optimal policy in the limit.
Tasks	Q-Learning
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02552v1
PDF	https://arxiv.org/pdf/1912.02552v1.pdf
PWC	https://paperswithcode.com/paper/191202552
Repo
Framework

Learning Fast Matching Models from Weak Annotations


Title	Learning Fast Matching Models from Weak Annotations
Authors	Xue Li, Zhipeng Luo, Hao Sun, Jianjin Zhang, Weihao Han, Xianqi Chu, Liangjie Zhang, Qi Zhang
Abstract	This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment of inseparable architectures, and hence greatly limits the model accuracy. The second problem arises from the heavy dependency on human provided labels, which are expensive and time-consuming to collect, yet how to leverage unlabeled search log data is rarely studied. The proposed training framework targets on mitigating both issues, by treating the stronger but undeployable models as annotators, and learning a deployable model from both human provided relevance labels and weakly annotated search log data. Specifically, we first construct multiple auxiliary tasks from the enumerated relevance labels, and train the annotators by jointly learning from those related tasks. The annotation models are then used to assign scores to both labeled and unlabeled training samples. The deployable model is firstly learnt on the scored unlabeled data, and then fine-tuned on scored labeled data, by leveraging both labels and scores via minimizing the proposed label-aware weighted loss. According to our experiments, compared with the baseline that directly learns from relevance labels, training by the proposed framework outperforms it by a large margin, and improves data efficiency substantially by dispensing with 80% labeled samples. The proposed framework allows us to improve the fast matching model by learning from stronger annotators while keeping its architecture unchanged. Meanwhile, our training framework offers a principled manner to leverage search log data in the training phase, which could effectively alleviate our dependency on human provided labels.
Tasks
Published	2019-01-30
URL	http://arxiv.org/abs/1901.10710v3
PDF	http://arxiv.org/pdf/1901.10710v3.pdf
PWC	https://paperswithcode.com/paper/learning-fast-matching-models-from-weak
Repo
Framework

Multiple Independent Subspace Clusterings


Title	Multiple Independent Subspace Clusterings
Authors	Xing Wang, Jun Wang, Carlotta Domeniconi, Guoxian Yu, Guoqiang Xiao, Maozu Guo
Abstract	Multiple clustering aims at discovering diverse ways of organizing data into clusters. Despite the progress made, it’s still a challenge for users to analyze and understand the distinctive structure of each output clustering. To ease this process, we consider diverse clusterings embedded in different subspaces, and analyze the embedding subspaces to shed light into the structure of each clustering. To this end, we provide a two-stage approach called MISC (Multiple Independent Subspace Clusterings). In the first stage, MISC uses independent subspace analysis to seek multiple and statistical independent (i.e. non-redundant) subspaces, and determines the number of subspaces via the minimum description length principle. In the second stage, to account for the intrinsic geometric structure of samples embedded in each subspace, MISC performs graph regularized semi-nonnegative matrix factorization to explore clusters. It additionally integrates the kernel trick into matrix factorization to handle non-linearly separable clusters. Experimental results on synthetic datasets show that MISC can find different interesting clusterings from the sought independent subspaces, and it also outperforms other related and competitive approaches on real-world datasets.
Tasks
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04191v1
PDF	https://arxiv.org/pdf/1905.04191v1.pdf
PWC	https://paperswithcode.com/paper/multiple-independent-subspace-clusterings
Repo
Framework

Regression Constraint for an Explainable Cervical Cancer Classifier


Title	Regression Constraint for an Explainable Cervical Cancer Classifier
Authors	Antoine Pirovano, Leandro G. Almeida, Said Ladjal
Abstract	This article adresses the problem of automatic squamous cells classification for cervical cancer screening using Deep Learning methods. We study different architectures on a public dataset called Herlev dataset, which consists in classifying cells, obtained by cervical pap smear, regarding the severity of the abnormalities they represent. Furthermore, we use an attribution method to understand which cytomorphological features are actually learned as discriminative to classify severity of the abnormalities. Through this paper, we show how we trained a performant classifier: 74.5% accuracy on severity classification and 94% accuracy on normal/abnormal classification.
Tasks
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02650v2
PDF	https://arxiv.org/pdf/1908.02650v2.pdf
PWC	https://paperswithcode.com/paper/regression-constraint-for-an-explainable
Repo
Framework

Dense 3D Visual Mapping via Semantic Simplification


Title	Dense 3D Visual Mapping via Semantic Simplification
Authors	Luca Morreale, Andrea Romanoni, Matteo Matteucci
Abstract	Dense 3D visual mapping estimates as many as possible pixel depths, for each image. This results in very dense point clouds that often contain redundant and noisy information, especially for surfaces that are roughly planar, for instance, the ground or the walls in the scene. In this paper we leverage on semantic image segmentation to discriminate which regions of the scene require simplification and which should be kept at high level of details. We propose four different point cloud simplification methods which decimate the perceived point cloud by relying on class-specific local and global statistics still maintaining more points in the proximity of class boundaries to preserve the infra-class edges and discontinuities. 3D dense model is obtained by fusing the point clouds in a 3D Delaunay Triangulation to deal with variable point cloud density. In the experimental evaluation we have shown that, by leveraging on semantics, it is possible to simplify the model and diminish the noise affecting the point clouds.
Tasks	Semantic Segmentation
Published	2019-02-20
URL	http://arxiv.org/abs/1902.07511v1
PDF	http://arxiv.org/pdf/1902.07511v1.pdf
PWC	https://paperswithcode.com/paper/dense-3d-visual-mapping-via-semantic
Repo
Framework

Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy


Title	Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy
Authors	Kaiyu Yang, Klint Qinami, Li Fei-Fei, Jia Deng, Olga Russakovsky
Abstract	Computer vision technology is being used by many but remains representative of only a few. People have reported misbehavior of computer vision models, including offensive prediction results and lower performance for underrepresented groups. Current computer vision models are typically developed using datasets consisting of manually annotated images or videos; the data and label distributions in these datasets are critical to the models’ behavior. In this paper, we examine ImageNet, a large-scale ontology of images that has spurred the development of many modern computer vision methods. We consider three key factors within the “person” subtree of ImageNet that may lead to problematic behavior in downstream computer vision technology: (1) the stagnant concept vocabulary of WordNet, (2) the attempt at exhaustive illustration of all categories with images, and (3) the inequality of representation in the images within concepts. We seek to illuminate the root causes of these concerns and take the first steps to mitigate them constructively.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07726v1
PDF	https://arxiv.org/pdf/1912.07726v1.pdf
PWC	https://paperswithcode.com/paper/towards-fairer-datasets-filtering-and
Repo
Framework

Learning from Context: Exploiting and Interpreting File Path Information for Better Malware Detection


Title	Learning from Context: Exploiting and Interpreting File Path Information for Better Malware Detection
Authors	Adarsh Kyadige, Ethan M. Rudd, Konstantin Berlin
Abstract	Machine learning (ML) used for static portable executable (PE) malware detection typically employs per-file numerical feature vector representations as input with one or more target labels during training. However, there is much orthogonal information that can be gleaned from the \textit{context} in which the file was seen. In this paper, we propose utilizing a static source of contextual information – the path of the PE file – as an auxiliary input to the classifier. While file paths are not malicious or benign in and of themselves, they do provide valuable context for a malicious/benign determination. Unlike dynamic contextual information, file paths are available with little overhead and can seamlessly be integrated into a multi-view static ML detector, yielding higher detection rates at very high throughput with minimal infrastructural changes. Here we propose a multi-view neural network, which takes feature vectors from PE file content as well as corresponding file paths as inputs and outputs a detection score. To ensure realistic evaluation, we use a dataset of approximately 10 million samples – files and file paths from user endpoints of an actual security vendor network. We then conduct an interpretability analysis via LIME modeling to ensure that our classifier has learned a sensible representation and see which parts of the file path most contributed to change in the classifier’s score. We find that our model learns useful aspects of the file path for classification, while also learning artifacts from customers testing the vendor’s product, e.g., by downloading a directory of malware samples each named as their hash. We prune these artifacts from our test dataset and demonstrate reductions in false negative rate of 32.3% at a $10^{-3}$ false positive rate (FPR) and 33.1% at $10^{-4}$ FPR, over a similar topology single input PE file content only model.
Tasks	Malware Detection
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06987v1
PDF	https://arxiv.org/pdf/1905.06987v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-context-exploiting-and
Repo
Framework