April 1, 2020

3113 words 15 mins read

Paper Group ANR 452

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey. A Simple and Agile Cloud Infrastructure to Support Cybersecurity Oriented Machine Learning Workflows. 3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans. Interaction Graphs for Object Importance Estimation in On-road Driving Videos. LA …

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey


Title	Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Authors	Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer
Abstract	In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative. However, direct transfer often results in significant performance decay due to domain shift. Domain adaptation (DA) addresses this problem by minimizing the impact of domain shift between the source and target domains. Multi-source domain adaptation (MDA) is a powerful extension in which the labeled data may be collected from multiple sources with different distributions. Due to the success of DA methods and the prevalence of multi-source data, MDA has attracted increasing attention in both academia and industry. In this survey, we define various MDA strategies and summarize available datasets for evaluation. We also compare modern MDA methods in the deep learning era, including latent space transformation and intermediate domain generation. Finally, we discuss future research directions for MDA.
Tasks	Domain Adaptation
Published	2020-02-26
URL	https://arxiv.org/abs/2002.12169v1
PDF	https://arxiv.org/pdf/2002.12169v1.pdf
PWC	https://paperswithcode.com/paper/multi-source-domain-adaptation-in-the-deep
Repo
Framework

A Simple and Agile Cloud Infrastructure to Support Cybersecurity Oriented Machine Learning Workflows


Title	A Simple and Agile Cloud Infrastructure to Support Cybersecurity Oriented Machine Learning Workflows
Authors	Konstantin Berlin, Ajay Lakshminarayanarao
Abstract	Generating up to date, well labeled datasets for machine learning (ML) security models is a unique engineering challenge, as large data volumes, complexity of labeling, and constant concept drift makes it difficult to generate effective training datasets. Here we describe a simple, resilient cloud infrastructure for generating ML training and testing datasets, that has enhanced the speed at which our team is able to research and keep in production a multitude of security ML models.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11828v1
PDF	https://arxiv.org/pdf/2002.11828v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-and-agile-cloud-infrastructure-to
Repo
Framework

3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans


Title	3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans
Authors	Antoni Rosinol, Arjun Gupta, Marcus Abate, Jingnan Shi, Luca Carlone
Abstract	We present a unified representation for actionable spatial perception: 3D Dynamic Scene Graphs. Scene graphs are directed graphs where nodes represent entities in the scene (e.g. objects, walls, rooms), and edges represent relations (e.g. inclusion, adjacency) among nodes. Dynamic scene graphs (DSGs) extend this notion to represent dynamic scenes with moving agents (e.g. humans, robots), and to include actionable information that supports planning and decision-making (e.g. spatio-temporal relations, topology at different levels of abstraction). Our second contribution is to provide the first fully automatic Spatial PerceptIon eNgine(SPIN) to build a DSG from visual-inertial data. We integrate state-of-the-art techniques for object and human detection and pose estimation, and we describe how to robustly infer object, robot, and human nodes in crowded scenes. To the best of our knowledge, this is the first paper that reconciles visual-inertial SLAM and dense human mesh tracking. Moreover, we provide algorithms to obtain hierarchical representations of indoor environments (e.g. places, structures, rooms) and their relations. Our third contribution is to demonstrate the proposed spatial perception engine in a photo-realistic Unity-based simulator, where we assess its robustness and expressiveness. Finally, we discuss the implications of our proposal on modern robotics applications. 3D Dynamic Scene Graphs can have a profound impact on planning and decision-making, human-robot interaction, long-term autonomy, and scene prediction. A video abstract is available at https://youtu.be/SWbofjhyPzI
Tasks	Decision Making, Human Detection, Pose Estimation
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06289v1
PDF	https://arxiv.org/pdf/2002.06289v1.pdf
PWC	https://paperswithcode.com/paper/3d-dynamic-scene-graphs-actionable-spatial
Repo
Framework

Interaction Graphs for Object Importance Estimation in On-road Driving Videos


Title	Interaction Graphs for Object Importance Estimation in On-road Driving Videos
Authors	Zehua Zhang, Ashish Tawari, Sujitha Martin, David Crandall
Abstract	A vehicle driving along the road is surrounded by many objects, but only a small subset of them influence the driver’s decisions and actions. Learning to estimate the importance of each object on the driver’s real-time decision-making may help better understand human driving behavior and lead to more reliable autonomous driving systems. Solving this problem requires models that understand the interactions between the ego-vehicle and the surrounding objects. However, interactions among other objects in the scene can potentially also be very helpful, e.g., a pedestrian beginning to cross the road between the ego-vehicle and the car in front will make the car in front less important. We propose a novel framework for object importance estimation using an interaction graph, in which the features of each object node are updated by interacting with others through graph convolution. Experiments show that our model outperforms state-of-the-art baselines with much less input and pre-processing.
Tasks	Autonomous Driving, Decision Making
Published	2020-03-12
URL	https://arxiv.org/abs/2003.06045v1
PDF	https://arxiv.org/pdf/2003.06045v1.pdf
PWC	https://paperswithcode.com/paper/interaction-graphs-for-object-importance
Repo
Framework

LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning


Title	LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning
Authors	Tianyi Chen, Yuejiao Sun, Wotao Yin
Abstract	This paper targets solving distributed machine learning problems such as federated learning in a communication-efficient fashion. A class of new stochastic gradient descent (SGD) approaches have been developed, which can be viewed as the stochastic generalization to the recently developed lazily aggregated gradient (LAG) method — justifying the name LASG. LAG adaptively predicts the contribution of each round of communication and chooses only the significant ones to perform. It saves communication while also maintains the rate of convergence. However, LAG only works with deterministic gradients, and applying it to stochastic gradients yields poor performance. The key components of LASG are a set of new rules tailored for stochastic gradients that can be implemented either to save download, upload, or both. The new algorithms adaptively choose between fresh and stale stochastic gradients and have convergence rates comparable to the original SGD. LASG achieves impressive empirical performance — it typically saves total communication by an order of magnitude.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11360v1
PDF	https://arxiv.org/pdf/2002.11360v1.pdf
PWC	https://paperswithcode.com/paper/lasg-lazily-aggregated-stochastic-gradients
Repo
Framework

Learning Hidden States in a Chaotic System: A Physics-Informed Echo State Network Approach


Title	Learning Hidden States in a Chaotic System: A Physics-Informed Echo State Network Approach
Authors	Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
Abstract	We extend the Physics-Informed Echo State Network (PI-ESN) framework to reconstruct the evolution of an unmeasured state (hidden state) in a chaotic system. The PI-ESN is trained by using (i) data, which contains no information on the unmeasured state, and (ii) the physical equations of a prototypical chaotic dynamical system. Non-noisy and noisy datasets are considered. First, it is shown that the PI-ESN can accurately reconstruct the unmeasured state. Second, the reconstruction is shown to be robust with respect to noisy data, which means that the PI-ESN acts as a denoiser. This paper opens up new possibilities for leveraging the synergy between physical knowledge and machine learning to enhance the reconstruction and prediction of unmeasured states in chaotic dynamical systems.
Tasks
Published	2020-01-06
URL	https://arxiv.org/abs/2001.02982v1
PDF	https://arxiv.org/pdf/2001.02982v1.pdf
PWC	https://paperswithcode.com/paper/learning-hidden-states-in-a-chaotic-system-a
Repo
Framework

Are You an Introvert or Extrovert? Accurate Classification With Only Ten Predictors


Title	Are You an Introvert or Extrovert? Accurate Classification With Only Ten Predictors
Authors	Chaehan So
Abstract	This paper investigates how accurately the prediction of being an introvert vs. extrovert can be made with less than ten predictors. The study is based on a previous data collection of 7161 respondents of a survey on 91 personality and 3 demographic items. The results show that it is possible to effectively reduce the size of this measurement instrument from 94 to 10 features with a performance loss of only 1%, achieving an accuracy of 73.81% on unseen data. Class imbalance correction methods like SMOTE or ADASYN showed considerable improvement on the validation set but only minor performance improvement on the testing set.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.01580v1
PDF	https://arxiv.org/pdf/2003.01580v1.pdf
PWC	https://paperswithcode.com/paper/are-you-an-introvert-or-extrovert-accurate
Repo
Framework

Stochastic Normalizing Flows


Title	Stochastic Normalizing Flows
Authors	Hao Wu, Jonas Köhler, Frank Noé
Abstract	Normalizing flows are popular generative learning methods that train an invertible function to transform a simple prior distribution into a complicated target distribution. Here we generalize the framework by introducing Stochastic Normalizing Flows (SNF) - an arbitrary sequence of deterministic invertible functions and stochastic processes such as Markov Chain Monte Carlo (MCMC) or Langevin Dynamics. This combination can be powerful as adding stochasticity to a flow helps overcoming expressiveness limitations of a chosen deterministic invertible function, while the trainable flow transformations can improve the sampling efficiency over pure MCMC. Key to our approach is that we can match a marginal target density without having to marginalize out the stochasticity of traversed paths. Invoking ideas from nonequilibrium statistical mechanics, we introduce a training method that only uses conditional path probabilities. We can turn an SNF into a Boltzmann Generator that samples asymptotically unbiased from a given target density by importance sampling of these paths. We illustrate the representational power, sampling efficiency and asymptotic correctness of SNFs on several benchmarks.
Tasks
Published	2020-02-16
URL	https://arxiv.org/abs/2002.06707v2
PDF	https://arxiv.org/pdf/2002.06707v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-normalizing-flows
Repo
Framework

Broadening Label-based Argumentation Semantics with May-Must Scales


Title	Broadening Label-based Argumentation Semantics with May-Must Scales
Authors	Ryuta Arisaka, Takayuki Ito
Abstract	The semantics as to which set of arguments in a given argumentation graph may be acceptable (acceptability semantics) can be characterised in a few different ways. Among them, labelling-based approach allows for concise and flexible determination of acceptability statuses of arguments through assignment of a label indicating acceptance, rejection, or undecided to each argument. In this work, we contemplate a way of broadening it by accommodating may- and must- conditions for an argument to be accepted or rejected, as determined by the number(s) of rejected and accepted attacking arguments. We show that the broadened label-based semantics can be used to express more mild indeterminacy than inconsistency for acceptability judgement when, for example, it may be the case that an argument is accepted and when it may also be the case that it is rejected. We identify that finding which conditions a labelling satisfies for every argument can be an undecidable problem, which has an unfavourable implication to semantics. We propose to address this problem by enforcing a labelling to maximally respect the conditions, while keeping the rest that would necessarily cause non-termination labelled undecided.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05730v2
PDF	https://arxiv.org/pdf/2001.05730v2.pdf
PWC	https://paperswithcode.com/paper/broadening-label-based-argumentation
Repo
Framework

Deep Multimodal Image-Text Embeddings for Automatic Cross-Media Retrieval


Title	Deep Multimodal Image-Text Embeddings for Automatic Cross-Media Retrieval
Authors	Hadi Abdi Khojasteh, Ebrahim Ansari, Parvin Razzaghi, Akbar Karimi
Abstract	This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are not comparable. In this work, we introduce an end-to-end deep multimodal convolutional-recurrent network for learning both vision and language representations simultaneously to infer image-text similarity. The model learns which pairs are a match (positive) and which ones are a mismatch (negative) using a hinge-based triplet ranking. To learn about the joint representations, we leverage our newly extracted collection of tweets from Twitter. The main characteristic of our dataset is that the images and tweets are not standardized the same as the benchmarks. Furthermore, there can be a higher semantic correlation between the pictures and tweets contrary to benchmarks in which the descriptions are well-organized. Experimental results on MS-COCO benchmark dataset show that our model outperforms certain methods presented previously and has competitive performance compared to the state-of-the-art. The code and dataset have been made available publicly.
Tasks	Cross-Modal Retrieval
Published	2020-02-23
URL	https://arxiv.org/abs/2002.10016v1
PDF	https://arxiv.org/pdf/2002.10016v1.pdf
PWC	https://paperswithcode.com/paper/deep-multimodal-image-text-embeddings-for
Repo
Framework


Title	A Novel Incremental Cross-Modal Hashing Approach
Authors	Devraj Mandal, Soma Biswas
Abstract	Cross-modal retrieval deals with retrieving relevant items from one modality, when provided with a search query from another modality. Hashing techniques, where the data is represented as binary bits have specifically gained importance due to the ease of storage, fast computations and high accuracy. In real world, the number of data categories is continuously increasing, which requires algorithms capable of handling this dynamic scenario. In this work, we propose a novel incremental cross-modal hashing algorithm termed “iCMH”, which can adapt itself to handle incoming data of new categories. The proposed approach consists of two sequential stages, namely, learning the hash codes and training the hash functions. At every stage, a small amount of old category data termed “exemplars” is is used so as not to forget the old data while trying to learn for the new incoming data, i.e. to avoid catastrophic forgetting. In the first stage, the hash codes for the exemplars is used, and simultaneously, hash codes for the new data is computed such that it maintains the semantic relations with the existing data. For the second stage, we propose both a non-deep and deep architectures to learn the hash functions effectively. Extensive experiments across a variety of cross-modal datasets and comparisons with state-of-the-art cross-modal algorithms shows the usefulness of our approach.
Tasks	Cross-Modal Retrieval
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00677v1
PDF	https://arxiv.org/pdf/2002.00677v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-incremental-cross-modal-hashing
Repo
Framework

Robust Boosting for Regression Problems


Title	Robust Boosting for Regression Problems
Authors	Xiaomeng Ju, Matías Salibián-Barrera
Abstract	The gradient boosting algorithm constructs a regression estimator using a linear combination of simple “base learners”. In order to obtain a robust non-parametric regression estimator that is scalable to high dimensional problems we propose a robust boosting algorithm based on a two-stage approach, similar to what is done for robust linear regression: we first minimize a robust residual scale estimator, and then improve its efficiency by optimizing a bounded loss function. Unlike previous proposals, our algorithm does not need to compute an ad-hoc residual scale estimator in each step. Since our loss functions are typically non-convex, we propose initializing our algorithm with an $L_1$ regression tree, which is fast to compute. We also introduce a robust variable importance metric for variable selection that is calculated via a permutation procedure. Through simulated and real data experiments, we compare our method against gradient boosting with squared loss and other robust boosting methods in the literature. With clean data, our method works equally well as gradient boosting with the squared loss. With symmetric and asymmetrically contaminated data, we show that our proposed method outperforms in terms of prediction error and variable selection accuracy.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02054v1
PDF	https://arxiv.org/pdf/2002.02054v1.pdf
PWC	https://paperswithcode.com/paper/robust-boosting-for-regression-problems
Repo
Framework

AdvJND: Generating Adversarial Examples with Just Noticeable Difference


Title	AdvJND: Generating Adversarial Examples with Just Noticeable Difference
Authors	Zifei Zhang, Kai Qiao, Lingyun Jiang, Linyuan Wang, Bin Yan
Abstract	Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a good-performance model to misclassify the crafted examples, without category differences in the human eyes, and fools deep models successfully. There are two requirements for generating adversarial examples: the attack success rate and image fidelity metrics. Generally, perturbations are increased to ensure the adversarial examples’ high attack success rate; however, the adversarial examples obtained have poor concealment. To alleviate the tradeoff between the attack success rate and image fidelity, we propose a method named AdvJND, adding visual model coefficients, just noticeable difference coefficients, in the constraint of a distortion function when generating adversarial examples. In fact, the visual subjective feeling of the human eyes is added as a priori information, which decides the distribution of perturbations, to improve the image quality of adversarial examples. We tested our method on the FashionMNIST, CIFAR10, and MiniImageNet datasets. Adversarial examples generated by our AdvJND algorithm yield gradient distributions that are similar to those of the original inputs. Hence, the crafted noise can be hidden in the original inputs, thus improving the attack concealment significantly.
Tasks	Image Classification
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00179v1
PDF	https://arxiv.org/pdf/2002.00179v1.pdf
PWC	https://paperswithcode.com/paper/advjnd-generating-adversarial-examples-with
Repo
Framework

Machine Education: Designing semantically ordered and ontologically guided modular neural networks


Title	Machine Education: Designing semantically ordered and ontologically guided modular neural networks
Authors	Hussein A. Abbass, Sondoss Elsawah, Eleni Petraki, Robert Hunjet
Abstract	The literature on machine teaching, machine education, and curriculum design for machines is in its infancy with sparse papers on the topic primarily focusing on data and model engineering factors to improve machine learning. In this paper, we first discuss selected attempts to date on machine teaching and education. We then bring theories and methodologies together from human education to structure and mathematically define the core problems in lesson design for machine education and the modelling approaches required to support the steps for machine education. Last, but not least, we offer an ontology-based methodology to guide the development of lesson plans to produce transparent and explainable modular learning machines, including neural networks.
Tasks
Published	2020-02-07
URL	https://arxiv.org/abs/2002.03841v1
PDF	https://arxiv.org/pdf/2002.03841v1.pdf
PWC	https://paperswithcode.com/paper/machine-education-designing-semantically
Repo
Framework

Gaussian Process Regression for Probabilistic Short-term Solar Output Forecast


Title	Gaussian Process Regression for Probabilistic Short-term Solar Output Forecast
Authors	Fatemeh Najibi, Dimitra Apostolopoulou, Eduardo Alonso
Abstract	With increasing concerns of climate change, renewable resources such as photovoltaic (PV) have gained popularity as a means of energy generation. The smooth integration of such resources in power system operations is enabled by accurate forecasting mechanisms that address their inherent intermittency and variability. This paper proposes a probabilistic framework to predict short-term PV output taking into account the uncertainty of weather. To this end, we make use of datasets that comprise of power output and meteorological data such as irradiance, temperature, zenith, and azimuth. First, we categorise the data into four groups based on solar output and time by using k-means clustering. Next, a correlation study is performed to choose the weather features which affect solar output to a greater extent. Finally, we determine a function that relates the aforementioned selected features with solar output by using Gaussian Process Regression and Matern 5/2 as a kernel function. We validate our method with five solar generation plants in different locations and compare the results with existing methodologies. More specifically, in order to test the proposed model, two different methods are used: (i) 5-fold cross-validation; and (ii) holding out 30 random days as test data. To confirm the model accuracy, we apply our framework 30 independent times on each of the four clusters. The average error follows a normal distribution, and with 95% confidence level, it takes values between -1.6% to 1.4%.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.10878v1
PDF	https://arxiv.org/pdf/2002.10878v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-regression-for-probabilistic
Repo
Framework