January 31, 2020

3113 words 15 mins read

Paper Group ANR 26

VeREFINE: Integrating Object Pose Verification with Iterative Physics-guided Refinement. Soft Contextual Data Augmentation for Neural Machine Translation. Quality-based Pulse Estimation from NIR Face Video with Application to Driver Monitoring. A Probabilistic Framework to Node-level Anomaly Detection in Communication Networks. ALEX: An Updatable A …


Title	VeREFINE: Integrating Object Pose Verification with Iterative Physics-guided Refinement
Authors	Dominik Bauer, Timothy Patten, Markus Vincze
Abstract	Precise and robust object pose estimation for robotics applications requires verification and refinement steps. In this work, we propose to integrate hypotheses verification with object pose refinement guided by physics simulation. This allows the physical plausibility of individual object pose estimates and the stability of the estimated scene to be considered in a unified optimization. The proposed method is able to adapt to scenes of multiple objects and efficiently focuses on refining the most promising object poses in multi-hypotheses scenarios. We call this integrated approach VeREFINE and evaluate it on three datasets with varying scene complexity. The generality of the approach is shown by using three state-of-the-art pose estimators and three baseline refiners. Results show improvements over all baselines and on all datasets. Furthermore, our approach is applied in real-world grasping experiments and outperforms competing methods in terms of grasp success rate.
Tasks	Pose Estimation
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05730v2
PDF	https://arxiv.org/pdf/1909.05730v2.pdf
PWC	https://paperswithcode.com/paper/verefine-integrating-object-pose-verification
Repo
Framework

Soft Contextual Data Augmentation for Neural Machine Translation


Title	Soft Contextual Data Augmentation for Neural Machine Translation
Authors	Jinhua Zhu, Fei Gao, Lijun Wu, Yingce Xia, Tao Qin, Wengang Zhou, Xueqi Cheng, Tie-Yan Liu
Abstract	While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a language model) over the vocabulary, i.e., replacing the embedding of this word by a weighted combination of multiple semantically similar words. Since the weights of those words depend on the contextual information of the word to be replaced, the newly generated sentences capture much richer information than previous augmentation methods. Experimental results on both small scale and large scale machine translation datasets demonstrate the superiority of our method over strong baselines.
Tasks	Data Augmentation, Language Modelling, Machine Translation
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10523v1
PDF	https://arxiv.org/pdf/1905.10523v1.pdf
PWC	https://paperswithcode.com/paper/soft-contextual-data-augmentation-for-neural
Repo
Framework

Quality-based Pulse Estimation from NIR Face Video with Application to Driver Monitoring


Title	Quality-based Pulse Estimation from NIR Face Video with Application to Driver Monitoring
Authors	Javier Hernandez-Ortega, Shigenori Nagae, Julian Fierrez, Aythami Morales
Abstract	In this paper we develop a robust for heart rate (HR) estimation method using face video for challenging scenarios with high variability sources such as head movement, illumination changes, vibration, blur, etc. Our method employs a quality measure Q to extract a remote Plethysmography (rPPG) signal as clean as possible from a specific face video segment. Our main motivation is developing robust technology for driver monitoring. Therefore, for our experiments we use a self-collected dataset consisting of Near Infrared (NIR) videos acquired with a camera mounted in the dashboard of a real moving car. We compare the performance of a classic rPPG algorithm, and the performance of the same method, but using Q for selecting which video segments present a lower amount of variability. Our results show that using the video segments with the highest quality in a realistic driving setup improves the HR estimation with a relative accuracy improvement larger than 20%.
Tasks
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06568v2
PDF	https://arxiv.org/pdf/1905.06568v2.pdf
PWC	https://paperswithcode.com/paper/quality-based-pulse-estimation-from-nir-face
Repo
Framework

A Probabilistic Framework to Node-level Anomaly Detection in Communication Networks


Title	A Probabilistic Framework to Node-level Anomaly Detection in Communication Networks
Authors	Batiste Le Bars, Argyris Kalogeratos
Abstract	In this paper we consider the task of detecting abnormal communication volume occurring at node-level in communication networks. The signal of the communication activity is modeled by means of a clique stream: each occurring communication event is instantaneous and activates an undirected subgraph spanning over a set of equally participating nodes. We present a probabilistic framework to model and assess the communication volume observed at any single node. Specifically, we employ non-parametric regression to learn the probability that a node takes part in a certain event knowing the set of other nodes that are involved. On the top of that, we present a concentration inequality around the estimated volume of events in which a node could participate, which in turn allows us to build an efficient and interpretable anomaly scoring function. Finally, the superior performance of the proposed approach is empirically demonstrated in real-world sensor network data, as well as using synthetic communication activity that is in accordance with that latter setting.
Tasks	Anomaly Detection
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04521v1
PDF	http://arxiv.org/pdf/1902.04521v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-framework-to-node-level
Repo
Framework

ALEX: An Updatable Adaptive Learned Index


Title	ALEX: An Updatable Adaptive Learned Index
Authors	Jialin Ding, Umar Farooq Minhas, Hantian Zhang, Yinan Li, Chi Wang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, David Lomet
Abstract	Recent work on “learned indexes” has revolutionized the way we look at the decades-old field of DBMS indexing. The key idea is that indexes are “models” that predict the position of a key in a dataset. Indexes can, thus, be learned. The original work by Kraska et al. shows surprising results in terms of search performance and space requirements: A learned index beats a B+Tree by a factor of up to three in search time and by an order of magnitude in memory footprint, however it is limited to static, read-only workloads. This paper presents a new class of learned indexes called ALEX which addresses issues that arise when implementing dynamic, updatable learned indexes. Compared to the learned index from Kraska et al., ALEX has up to 3000X lower space requirements, but has up to 2.7X higher search performance on static workloads. Compared to a B+Tree, ALEX achieves up to 3.5X and 3.3X higher performance on static and some dynamic workloads, respectively, with up to 5 orders of magnitude smaller index size. Our detailed experiments show that ALEX presents a key step towards making learned indexes practical for a broader class of database workloads with dynamic updates.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08898v1
PDF	https://arxiv.org/pdf/1905.08898v1.pdf
PWC	https://paperswithcode.com/paper/alex-an-updatable-adaptive-learned-index
Repo
Framework

Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification


Title	Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification
Authors	Yangru Huang, Peixi Peng, Yi Jin, Junliang Xing, Congyan Lang, Songhe Feng
Abstract	Person re-identification (Re-ID) across multiple datasets is a challenging yet important task due to the possibly large distinctions between different datasets and the lack of training samples in practical applications. This work proposes a novel unsupervised domain adaption framework which transfers discriminative representations from the labeled source domain (dataset) to the unlabeled target domain (dataset). We propose to formulate the domain adaption task as an one-class classification problem with a novel domain similarity loss. Given the feature map of any image from a backbone network, a novel domain adaptive attention model (DAAM) first automatically learns to separate the feature map of an image to a domain-shared feature (DSH) map and a domain-specific feature (DSP) map simultaneously. Specially, the residual attention mechanism is designed to model DSP feature map for avoiding negative transfer. Then, a DSH branch and a DSP branch are introduced to learn DSH and DSP feature maps respectively. To reduce domain divergence caused by that the source and target datasets are collected from different environments, we force to project the DSH feature maps from different domains to a new nominal domain, and a novel domain similarity loss is proposed based on one-class classification. In addition, a novel unsupervised person Re-ID loss is proposed to take full use of unlabeled target data. Extensive experiments on the Market-1501 and DukeMTMC-reID benchmarks demonstrate state-of-the-art performance of the proposed method. Code will be released to facilitate further studies on the cross-domain person re-identification task.
Tasks	Domain Adaptation, Person Re-Identification
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10529v1
PDF	https://arxiv.org/pdf/1905.10529v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptive-attention-model-for
Repo
Framework

Geomancer: An Open-Source Framework for Geospatial Feature Engineering


Title	Geomancer: An Open-Source Framework for Geospatial Feature Engineering
Authors	Lester James V. Miranda, Mark Steve Samson, Alfiero K. Orden II, Bianca S. Silmaro, Ram K. De Guzman III, Stephanie S. Sy
Abstract	This paper presents Geomancer, an open-source framework for geospatial feature engineering. It simplifies the acquisition of geospatial attributes for downstream, large-scale machine learning tasks. Geomancer leverages any geospatial dataset stored in a data warehouse, users need only to define the features (Spells) they want to create, and cast them on any spatial dataset. In addition, these features can be exported into a JSON file (SpellBook) for sharing and reproducibility. Geomancer has been useful to some of our production use-cases such as property value estimation, area valuation, and more. It is available on Github, and can be installed from PyPI.
Tasks	Feature Engineering
Published	2019-10-12
URL	https://arxiv.org/abs/1910.05571v1
PDF	https://arxiv.org/pdf/1910.05571v1.pdf
PWC	https://paperswithcode.com/paper/geomancer-an-open-source-framework-for
Repo
Framework

Achieving Differential Privacy in Vertically Partitioned Multiparty Learning


Title	Achieving Differential Privacy in Vertically Partitioned Multiparty Learning
Authors	Depeng Xu, Shuhan Yuan, Xintao Wu
Abstract	Preserving differential privacy has been well studied under centralized setting. However, it’s very challenging to preserve differential privacy under multiparty setting, especially for the vertically partitioned case. In this work, we propose a new framework for differential privacy preserving multiparty learning in the vertically partitioned setting. Our core idea is based on the functional mechanism that achieves differential privacy of the released model by adding noise to the objective function. We show the server can simply dissect the objective function into single-party and cross-party sub-functions, and allocate computation and perturbation of their polynomial coefficients to local parties. Our method needs only one round of noise addition and secure aggregation. The released model in our framework achieves the same utility as applying the functional mechanism in the centralized setting. Evaluation on real-world and synthetic datasets for linear and logistic regressions shows the effectiveness of our proposed method.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04587v1
PDF	https://arxiv.org/pdf/1911.04587v1.pdf
PWC	https://paperswithcode.com/paper/achieving-differential-privacy-in-vertically
Repo
Framework

Can Intelligent Hyperparameter Selection Improve Resistance to Adversarial Examples?


Title	Can Intelligent Hyperparameter Selection Improve Resistance to Adversarial Examples?
Authors	Cody Burkard, Brent Lagesse
Abstract	Convolutional Neural Networks and Deep Learning classification systems in general have been shown to be vulnerable to attack by specially crafted data samples that appear to belong to one class but are instead classified as another, commonly known as adversarial examples. A variety of attack strategies have been proposed to craft these samples; however, there is no standard model that is used to compare the success of each type of attack. Furthermore, there is no literature currently available that evaluates how common hyperparameters and optimization strategies may impact a model’s ability to resist these samples. This research bridges that lack of awareness and provides a means for the selection of training and model parameters in future research on evasion attacks against convolutional neural networks. The findings of this work indicate that the selection of model hyperparameters does impact the ability of a model to resist attack, although they alone cannot prevent the existence of adversarial examples.
Tasks
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05586v1
PDF	http://arxiv.org/pdf/1902.05586v1.pdf
PWC	https://paperswithcode.com/paper/can-intelligent-hyperparameter-selection
Repo
Framework

Class-Conditional VAE-GAN for Local-Ancestry Simulation


Title	Class-Conditional VAE-GAN for Local-Ancestry Simulation
Authors	Daniel Mas Montserrat, Carlos Bustamante, Alexander Ioannidis
Abstract	Local ancestry inference (LAI) allows identification of the ancestry of all chromosomal segments in admixed individuals, and it is a critical step in the analysis of human genomes with applications from pharmacogenomics and precision medicine to genome-wide association studies. In recent years, many LAI techniques have been developed in both industry and academic research. However, these methods require large training data sets of human genomic sequences from the ancestries of interest. Such reference data sets are usually limited, proprietary, protected by privacy restrictions, or otherwise not accessible to the public. Techniques to generate training samples that resemble real haploid sequences from ancestries of interest can be useful tools in such scenarios, since a generalized model can often be shared, but the unique human sample sequences cannot. In this work we present a class-conditional VAE-GAN to generate new human genomic sequences that can be used to train local ancestry inference (LAI) algorithms. We evaluate the quality of our generated data by comparing the performance of a state-of-the-art LAI method when trained with generated versus real data.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.13220v1
PDF	https://arxiv.org/pdf/1911.13220v1.pdf
PWC	https://paperswithcode.com/paper/class-conditional-vae-gan-for-local-ancestry
Repo
Framework


Title	Graph Embedding Based Hybrid Social Recommendation System
Authors	Vishwas Sathish, Tanya Mehrotra, Simran Dhinwa, Bhaskarjyoti Das
Abstract	Item recommendation tasks are a widely studied topic. Recent developments in deep learning and spectral methods paved a path towards efficient graph embedding techniques. But little research has been done on applying these graph embedding to social graphs for recommendation tasks. This paper focuses at performance of various embedding methods applied on social graphs for the task of item recommendation. Additionally, a hybrid model is proposed wherein chosen embedding models are combined together to give a collective output. We put forward the hypothesis that such a hybrid model would perform better than individual embedding for recommendation task. With recommendation using individual embedding as a baseline, performance for hybrid model for the same task is evaluated and compared. Standard metrics are used for qualitative comparison. It is found that the proposed hybrid model outperforms the baseline.
Tasks	Graph Embedding
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09454v1
PDF	https://arxiv.org/pdf/1908.09454v1.pdf
PWC	https://paperswithcode.com/paper/graph-embedding-based-hybrid-social
Repo
Framework

Pitako – Recommending Game Design Elements in Cicero


Title	Pitako – Recommending Game Design Elements in Cicero
Authors	Tiago Machado, Dan Gopstein, Andy Nealen, Julian Togelius
Abstract	Recommender Systems are widely and successfully applied in e-commerce. Could they be used for design? In this paper, we introduce Pitako1, a tool that applies the Recommender System concept to assist humans in creative tasks. More specifically, Pitako provides suggestions by taking games designed by humans as inputs, and recommends mechanics and dynamics as outputs. Pitako is implemented as a new system within the mixed-initiative AI-based Game Design Assistant, Cicero. This paper discusses the motivation behind the implementation of Pitako as well as its technical details and presents usage examples. We believe that Pitako can influence the use of recommender systems to help humans in their daily tasks.
Tasks	Recommendation Systems
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03877v1
PDF	https://arxiv.org/pdf/1907.03877v1.pdf
PWC	https://paperswithcode.com/paper/pitako-recommending-game-design-elements-in
Repo
Framework

Semi-supervised Adversarial Active Learning on Attributed Graphs


Title	Semi-supervised Adversarial Active Learning on Attributed Graphs
Authors	Yayong Li, Jie Yin, Ling Chen
Abstract	Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional independent and identically distributed (i.i.d.) data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on graphs attempt to reuse the classic AL query strategies designed for i.i.d. data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labelled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way. Our framework learns two adversarial components: a graph embedding network that encodes both the unlabelled and labelled nodes into a latent space, expecting to trick the discriminator to regard all nodes as already labelled, and a semi-supervised discriminator network that distinguishes the unlabelled from the existing labelled nodes in the latent space. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labelled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other towards enhancing the active learning performance. Extensive experiments on four real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines.
Tasks	Active Learning, Graph Embedding
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08169v1
PDF	https://arxiv.org/pdf/1908.08169v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-adversarial-active-learning
Repo
Framework

ReLU Networks as Surrogate Models in Mixed-Integer Linear Programs


Title	ReLU Networks as Surrogate Models in Mixed-Integer Linear Programs
Authors	Bjarne Grimstad, Henrik Andersson
Abstract	We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation of ReLU networks has recently been applied by many authors to probe for various model properties subject to input bounds. The formulation is obtained by programming each ReLU operator with a binary variable and applying the big-M method. The efficiency of the formulation hinges on the tightness of the bounds defined by the big-M values. When ReLU networks are embedded in a larger optimization problem, the presence of output bounds can be exploited in bound tightening. To this end, we devise and study several bound tightening procedures that consider both input and output bounds. Our numerical results show that bound tightening may reduce solution times considerably, and that small-sized ReLU networks are suitable as surrogate models in mixed-integer linear programs.
Tasks
Published	2019-07-06
URL	https://arxiv.org/abs/1907.03140v3
PDF	https://arxiv.org/pdf/1907.03140v3.pdf
PWC	https://paperswithcode.com/paper/relu-networks-as-surrogate-models-in-mixed
Repo
Framework

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning


Title	Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning
Authors	Yanchao Sun, Furong Huang
Abstract	Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dynamics of any state-action pair from known state-action pairs before meeting it for sufficient times. We propose a new model-based method called Greedy Inference Model (GIM) that infers the unknown dynamics from known dynamics based on the internal spectral properties of the environment. In other words, GIM can “learn by analogy”. We further introduce a new exploration strategy which ensures that the agent rapidly and evenly visits unknown state-action pairs. GIM is much more computationally efficient than state-of-the-art model-based algorithms, as the number of dynamic programming operations is independent of the environment size. Lower sample complexity could also be achieved under mild conditions compared against methods without inferring. Experimental results demonstrate the effectiveness and efficiency of GIM in a variety of real-world tasks.
Tasks
Published	2019-12-21
URL	https://arxiv.org/abs/1912.10329v3
PDF	https://arxiv.org/pdf/1912.10329v3.pdf
PWC	https://paperswithcode.com/paper/can-agents-learn-by-analogy-an-inferable
Repo
Framework