January 28, 2020

3512 words 17 mins read

Paper Group ANR 965

SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction. Generating and Aligning from Data Geometries with Generative Adversarial Networks. Transformed $\ell_1$ Regularization for Learning Sparse Deep Neural Networks. TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Pr …

SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction


Title	SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
Authors	Bo Chen, Decai Li, Yuqing He, Chunsheng Hua
Abstract	Technologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do not consider the mining of relationships, which include spatial relationships between human and scene elements as well as causal relationships in temporal action sequences. In fact, human beings are good at using spatial and causal relational reasoning mechanism to predict the actions of others. Inspired by this idea, we proposed a Spatial and Causal Relationship based Graph Reasoning Network (SCR-Graph), which can be used to predict human actions by modeling the action-scene relationship, and causal relationship between actions, in spatial and temporal dimensions respectively. Here, in spatial dimension, a hierarchical graph attention module is designed by iteratively aggregating the features of different kinds of scene elements in different level. In temporal dimension, we designed a knowledge graph based causal reasoning module and map the past actions to temporal causal features through Diffusion RNN. Finally, we integrated the causality features into the heterogeneous graph in the form of shadow node, and introduced a self-attention module to determine the time when the knowledge graph information should be activated. Extensive experimental results on the VIRAT datasets demonstrate the favorable performance of the proposed framework.
Tasks	Autonomous Driving, Relational Reasoning
Published	2019-11-22
URL	https://arxiv.org/abs/1912.05003v1
PDF	https://arxiv.org/pdf/1912.05003v1.pdf
PWC	https://paperswithcode.com/paper/scr-graph-spatial-causal-relationships-based
Repo
Framework

Generating and Aligning from Data Geometries with Generative Adversarial Networks


Title	Generating and Aligning from Data Geometries with Generative Adversarial Networks
Authors	Matthew Amodio, Smita Krishnaswamy
Abstract	Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption. These models map between two domains by fooling a probabilistic discriminator, thereby matching the probability distributions of the real and generated data. Instead of this probabilistic approach, we cast the problem in terms of aligning the geometry of the manifolds of the two domains. We introduce the Manifold Geometry Matching Generative Adversarial Network (MGM GAN), which adds two novel mechanisms to facilitate GANs sampling from the geometry of the manifold rather than the density and then aligning two manifold geometries: (1) an importance sampling technique that reweights points based on their density on the manifold, making the discriminator only able to discern geometry and (2) a penalty adapted from traditional manifold alignment literature that explicitly enforces the geometry to be preserved. The MGM GAN leverages the manifolds arising from a pre-trained autoencoder to bridge the gap between formal manifold alignment literature and existing GAN work, and demonstrate the advantages of modeling the manifold geometry over its density.
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08177v1
PDF	http://arxiv.org/pdf/1901.08177v1.pdf
PWC	https://paperswithcode.com/paper/generating-and-aligning-from-data-geometries
Repo
Framework

Transformed $\ell_1$ Regularization for Learning Sparse Deep Neural Networks


Title	Transformed $\ell_1$ Regularization for Learning Sparse Deep Neural Networks
Authors	Rongrong Ma, Jianyu Miao, Lingfeng Niu, Peng Zhang
Abstract	Deep neural networks (DNNs) have achieved extraordinary success in numerous areas. However, to attain this success, DNNs often carry a large number of weight parameters, leading to heavy costs of memory and computation resources. Overfitting is also likely to happen in such network when the training data are insufficient. These shortcomings severely hinder the application of DNNs in resource-constrained platforms. In fact, many network weights are known to be redundant and can be removed from the network without much loss of performance. To this end, we introduce a new non-convex integrated transformed $\ell_1$ regularizer to promote sparsity for DNNs, which removes both redundant connections and unnecessary neurons simultaneously. To be specific, we apply the transformed $\ell_1$ to the matrix space of network weights and utilize it to remove redundant connections. Besides, group sparsity is also employed as an auxiliary to remove unnecessary neurons. An efficient stochastic proximal gradient algorithm is presented to solve the new model at the same time. To the best of our knowledge, this is the first work to utilize a non-convex regularizer in sparse optimization based method to promote sparsity for DNNs. Experiments on several public datasets demonstrate the effectiveness of the proposed method.
Tasks
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01021v1
PDF	http://arxiv.org/pdf/1901.01021v1.pdf
PWC	https://paperswithcode.com/paper/transformed-ell_1-regularization-for-learning
Repo
Framework

TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction


Title	TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
Authors	Ling Cai, Bo Yan, Gengchen Mai, Krzysztof Janowicz, Rui Zhu
Abstract	Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relation and entity embeddings are learned simultaneously. To handle heterogeneous relations in KGs, we introduce a novel way of representing heterogeneous neighborhood by introducing transformation assumptions on the relationship between the subject, the relation, and the object of a triple. Specifically, a relation is treated as a transformation operator transforming a head entity to a tail entity. Both translation assumption in TransE and rotation assumption in RotatE are explored in our framework. Additionally, instead of only learning entity embeddings in the convolution-based encoder while learning relation embeddings in the decoder as done by the state-of-art models, e.g., R-GCN, the TransGCN framework trains relation embeddings and entity embeddings simultaneously during the graph convolution operation, thus having fewer parameters compared with R-GCN. Experiments show that our models outperform the-state-of-arts methods on both FB15K-237 and WN18RR.
Tasks	Entity Embeddings, Knowledge Graphs, Link Prediction, Relational Reasoning
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00702v1
PDF	https://arxiv.org/pdf/1910.00702v1.pdf
PWC	https://paperswithcode.com/paper/transgcncoupling-transformation-assumptions
Repo
Framework

Semantic Referee: A Neural-Symbolic Framework for Enhancing Geospatial Semantic Segmentation


Title	Semantic Referee: A Neural-Symbolic Framework for Enhancing Geospatial Semantic Segmentation
Authors	Marjan Alirezaie, Martin Längkvist, Michael Sioutis, Amy Loutfi
Abstract	Understanding why machine learning algorithms may fail is usually the task of the human expert that uses domain knowledge and contextual information to discover systematic shortcomings in either the data or the algorithm. In this paper, we propose a semantic referee, which is able to extract qualitative features of the errors emerging from deep machine learning frameworks and suggest corrections. The semantic referee relies on ontological reasoning about spatial knowledge in order to characterize errors in terms of their spatial relations with the environment. Using semantics, the reasoner interacts with the learning algorithm as a supervisor. In this paper, the proposed method of the interaction between a neural network classifier and a semantic referee shows how to improve the performance of semantic segmentation for satellite imagery data.
Tasks	Semantic Segmentation
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13196v1
PDF	http://arxiv.org/pdf/1904.13196v1.pdf
PWC	https://paperswithcode.com/paper/semantic-referee-a-neural-symbolic-framework
Repo
Framework

Thompson Sampling for Adversarial Bit Prediction


Title	Thompson Sampling for Adversarial Bit Prediction
Authors	Yuval Lewi, Haim Kaplan, Yishay Mansour
Abstract	We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length $T$ with $k < \frac{T}{2}$ zeros, the sequences of largest regret consist of alternating zeros and ones followed by the remaining ones, and the sequence of smallest regret consists of ones followed by zeros. We also bound the regret of those sequences, the worse case sequences have regret $O(\sqrt{T})$ and the best case sequence have regret $O(1)$. We extend our results to a model where false positive and false negative errors have different weights. We characterize the sequences with largest expected regret in this generalized setting, and derive their regret bounds. We also show that there are sequences with $O(1)$ regret.
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09059v3
PDF	https://arxiv.org/pdf/1906.09059v3.pdf
PWC	https://paperswithcode.com/paper/thompson-sampling-for-adversarial-bit
Repo
Framework

The Limits of Efficiency for Open- and Closed-World Query Evaluation Under Guarded TGDs


Title	The Limits of Efficiency for Open- and Closed-World Query Evaluation Under Guarded TGDs
Authors	Pablo Barcelo, Victor Dalmau, Cristina Feier, Carsten Lutz, Andreas Pieris
Abstract	Ontology-mediated querying and querying in the presence of constraints are two key database problems where tuple-generating dependencies (TGDs) play a central role. In ontology-mediated querying, TGDs can formalize the ontology and thus derive additional facts from the given data, while in querying in the presence of constraints, they restrict the set of admissible databases. In this work, we study the limits of efficient query evaluation in the context of the above two problems, focussing on guarded and frontier-guarded TGDs and on UCQs as the actual queries. We show that a class of ontology-mediated queries (OMQs) based on guarded TGDs can be evaluated in FPT iff the OMQs in the class are equivalent to OMQs in which the actual query has bounded treewidth, up to some reasonable assumptions. For querying in the presence of constraints, we consider classes of constraint-query specifications (CQSs) that bundle a set of constraints with an actual query. We show a dichotomy result for CQSs based on guarded TGDs that parallels the one for OMQs except that, additionally, FPT coincides with PTime combined complexity. The proof is based on a novel connection between OMQ and CQS evaluation. Using a direct proof, we also show a similar dichotomy result, again up to some reasonable assumptions, for CQSs based on frontier-guarded TGDs with a bounded number of atoms in TGD heads. Our results on CQSs can be viewed as extensions of Grohe’s well-known characterization of the tractable classes of CQs (without constraints). Like Grohe’s characterization, all the above results assume that the arity of relation symbols is bounded by a constant. We also study the associated meta problems, i.e., whether a given OMQ or CQS is equivalent to one in which the actual query has bounded treewidth.
Tasks
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12442v1
PDF	https://arxiv.org/pdf/1912.12442v1.pdf
PWC	https://paperswithcode.com/paper/the-limits-of-efficiency-for-open-and-closed
Repo
Framework

Non-Parametric Adaptation for Neural Machine Translation


Title	Non-Parametric Adaptation for Neural Machine Translation
Authors	Ankur Bapna, Orhan Firat
Abstract	Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the other hand, non-parametric approaches are immune to forgetting, perfectly complementing the generalization ability of NMT. However, attempts to combine non-parametric or retrieval based approaches with NMT have only been successful on narrow domains, possibly due to over-reliance on sentence level retrieval. We propose a novel n-gram level retrieval approach that relies on local phrase level similarities, allowing us to retrieve neighbors that are useful for translation even when overall sentence similarity is low. We complement this with an expressive neural network, allowing our model to extract information from the noisy retrieved context. We evaluate our semi-parametric NMT approach on a heterogeneous dataset composed of WMT, IWSLT, JRC-Acquis and OpenSubtitles, and demonstrate gains on all 4 evaluation sets. The semi-parametric nature of our approach opens the door for non-parametric domain adaptation, demonstrating strong inference-time adaptation performance on new domains without the need for any parameter updates.
Tasks	Domain Adaptation, Machine Translation
Published	2019-02-28
URL	https://arxiv.org/abs/1903.00058v2
PDF	https://arxiv.org/pdf/1903.00058v2.pdf
PWC	https://paperswithcode.com/paper/non-parametric-adaptation-for-neural-machine
Repo
Framework

Sensitivity study of ANFIS model parameters to predict the pressure gradient with combined input and outputs hydrodynamics parameters in the bubble column reactor


Title	Sensitivity study of ANFIS model parameters to predict the pressure gradient with combined input and outputs hydrodynamics parameters in the bubble column reactor
Authors	Shahaboddin Shamshirband, Amir Mosavi, Kwok-wing Chau
Abstract	Intelligent algorithms are recently used in the optimization process in chemical engineering and application of multiphase flows such as bubbling flow. This overview of modeling can be a great replacement with complex numerical methods or very time-consuming and disruptive measurement experimental process. In this study, we develop the adaptive network-based fuzzy inference system (ANFIS) method for mapping inputs and outputs together and understand the behavior of the fluid flow from other output parameters of the bubble column reactor. Neural cells can fully learn the process in their memory and after the training stage, the fuzzy structure predicts the multiphase flow data. Four inputs such as x coordinate, y coordinate, z coordinate, and air superficial velocity and one output such as pressure gradient are considered in the learning process of the ANFIS method. During the learning process, the different number of the membership function, type of membership functions and the number of inputs are examined to achieve the intelligent algorithm with high accuracy. The results show that as the number of inputs increases the accuracy of the ANFIS method rises up to R^2>0.99 almost for all cases, while the increment in the number of rules has a effect on the intelligence of artificial algorithm. This finding shows that the density of neural objects or higher input parameters enables the moded for better understanding. We also proposed a new evaluation of data in the bubble column reactor by mapping inputs and outputs and shuffle all parameters together to understand the behaviour of the multiphase flow as a function of either inputs or outputs. This new process of mapping inputs and outputs data provides a framework to fully understand the flow in the fluid domain in a short time of fuzzy structure calculation.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.09309v1
PDF	https://arxiv.org/pdf/1907.09309v1.pdf
PWC	https://paperswithcode.com/paper/sensitivity-study-of-anfis-model-parameters
Repo
Framework

Learning Fitness Functions for Genetic Algorithms


Title	Learning Fitness Functions for Genetic Algorithms
Authors	Shantanu Mandal, Todd A. Anderson, Javier S. Turek, Justin Gottschlich, Shengtian Zhou, Abdullah Muzahid
Abstract	The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfully for many problems, one criticism is that hand-crafting its fitness function, the test that aims to effectively guide its evolution, can be notably challenging. Our framework presents a novel approach to learn the fitness function using neural networks to predict values of ideal fitness function. We also augment the evolutionary process with a minimally intrusive search heuristic. This heuristic improves the framework’s ability to discover correct programs from ones that are approximately correct and does so with negligible computational overhead. We compare our approach with two state-of-the-art program synthesis methods and demonstrate that it finds more correct programs with fewer candidate program generations.
Tasks	Program Synthesis
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08783v3
PDF	https://arxiv.org/pdf/1908.08783v3.pdf
PWC	https://paperswithcode.com/paper/netsyn-neural-evolutionary-technique-to
Repo
Framework

Privacy-preserving parametric inference: a case for robust statistics


Title	Privacy-preserving parametric inference: a case for robust statistics
Authors	Marco Avella-Medina
Abstract	Differential privacy is a cryptographically-motivated approach to privacy that has become a very active field of research over the last decade in theoretical computer science and machine learning. In this paradigm one assumes there is a trusted curator who holds the data of individuals in a database and the goal of privacy is to simultaneously protect individual data while allowing the release of global characteristics of the database. In this setting we introduce a general framework for parametric inference with differential privacy guarantees. We first obtain differentially private estimators based on bounded influence M-estimators by leveraging their gross-error sensitivity in the calibration of a noise term added to them in order to ensure privacy. We then show how a similar construction can also be applied to construct differentially private test statistics analogous to the Wald, score and likelihood ratio tests. We provide statistical guarantees for all our proposals via an asymptotic analysis. An interesting consequence of our results is to further clarify the connection between differential privacy and robust statistics. In particular, we demonstrate that differential privacy is a weaker stability requirement than infinitesimal robustness, and show that robust M-estimators can be easily randomized in order to guarantee both differential privacy and robustness towards the presence of contaminated data. We illustrate our results both on simulated and real data.
Tasks	Calibration
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10167v1
PDF	https://arxiv.org/pdf/1911.10167v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-parametric-inference-a
Repo
Framework

Support Vector Machine-Based Fire Outbreak Detection System


Title	Support Vector Machine-Based Fire Outbreak Detection System
Authors	Uduak Umoh, Edward Udo, Nyoho Emmanuel
Abstract	This study employed Support Vector Machine (SVM) in the classification and prediction of fire outbreak based on a fire outbreak dataset captured from the Fire Outbreak Data Capture Device (FODCD). The fire outbreak data capture device (FODCD) used was developed to capture the environmental parameters values used in this work. The FODCD device comprised a DHT11 temperature sensor, MQ-2 smoke sensor, LM393 Flame sensor, and ESP8266 Wi-Fi module, connected to Arduino nano v3.0.board. 700 data point was captured using the FODCD device, with 60% of the dataset used for training while 20% was used for testing and validation respectively. The SVM model was evaluated using the True Positive Rate (TPR), False Positive Rate (FPR), Accuracy, Error Rate (ER), Precision, and Recall performance metrics. The performance results show that the SVM algorithm can predict cases of fire outbreak with an accuracy of 80% and a minimal error rate of 0.2%. This system was able to predict cases of fire outbreak with a higher degree of accuracy. It is indicated that the use of sensors to capture real-world dataset and machine learning algorithm such as the support vector machine gives a better result to the problem of fire management.
Tasks
Published	2019-06-08
URL	https://arxiv.org/abs/1906.05655v1
PDF	https://arxiv.org/pdf/1906.05655v1.pdf
PWC	https://paperswithcode.com/paper/support-vector-machine-based-fire-outbreak
Repo
Framework

Faking Fairness via Stealthily Biased Sampling


Title	Faking Fairness via Stealthily Biased Sampling
Authors	Kazuto Fukuchi, Satoshi Hara, Takanori Maehara
Abstract	Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social communities. The question is whether such a fraud of the decision-maker is detectable so that the society can avoid the risk of fake fairness. In this study, we answer this question negatively. We specifically put our focus on a situation where the decision-maker publishes a benchmark dataset as the evidence of his/her fairness and attempts to deceive a person who uses an auditing tool that computes a fairness metric. To assess the (un)detectability of the fraud, we explicitly construct an algorithm, the stealthily biased sampling, that can deliberately construct an evil benchmark dataset via subsampling. We show that the fraud made by the stealthily based sampling is indeed difficult to detect both theoretically and empirically.
Tasks
Published	2019-01-24
URL	https://arxiv.org/abs/1901.08291v2
PDF	https://arxiv.org/pdf/1901.08291v2.pdf
PWC	https://paperswithcode.com/paper/pretending-fair-decisions-via-stealthily
Repo
Framework

Enhancing Explainability of Neural Networks through Architecture Constraints


Title	Enhancing Explainability of Neural Networks through Architecture Constraints
Authors	Zebin Yang, Aijun Zhang, Agus Sudjianto
Abstract	Prediction accuracy and model explainability are the two most important objectives when developing machine learning algorithms to solve real-world problems. The neural networks are known to possess good prediction performance, but lack of sufficient model interpretability. In this paper, we propose to enhance the explainability of neural networks through the following architecture constraints: a) sparse additive subnetworks; b) projection pursuit with orthogonality constraint; and c) smooth function approximation. It leads to an explainable neural network (xNN) with the superior balance between prediction performance and model interpretability. We derive the necessary and sufficient identifiability conditions for the proposed xNN model. The multiple parameters are simultaneously estimated by a modified mini-batch gradient descent method based on the backpropagation algorithm for calculating the derivatives and the Cayley transform for preserving the projection orthogonality. Through simulation study under six different scenarios, we compare the proposed method to several benchmarks including least absolute shrinkage and selection operator, support vector machine, random forest, extreme learning machine, and multi-layer perceptron. It is shown that the proposed xNN model keeps the flexibility of pursuing high prediction accuracy while attaining improved interpretability. Finally, a real data example is employed as a showcase application.
Tasks
Published	2019-01-12
URL	https://arxiv.org/abs/1901.03838v2
PDF	https://arxiv.org/pdf/1901.03838v2.pdf
PWC	https://paperswithcode.com/paper/enhancing-explainability-of-neural-networks
Repo
Framework

Image Captioning with Unseen Objects


Title	Image Captioning with Unseen Objects
Authors	Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
Abstract	Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within the captioning approach. Such models, however, tend to generate sentences which only consist of objects predicted by the recognition models, excluding instances of the classes without labelled training examples. In this paper, we propose a new challenging scenario that targets the image captioning problem in a fully zero-shot learning setting, where the goal is to be able to generate captions of test images containing objects that are not seen during training. The proposed approach jointly uses a novel zero-shot object detection model and a template-based sentence generator. Our experiments show promising results on the COCO dataset.
Tasks	Image Captioning, Object Detection, Object Recognition, Zero-Shot Learning, Zero-Shot Object Detection
Published	2019-07-31
URL	https://arxiv.org/abs/1908.00047v1
PDF	https://arxiv.org/pdf/1908.00047v1.pdf
PWC	https://paperswithcode.com/paper/image-captioning-with-unseen-objects
Repo
Framework