Incorporating Side Information by Adaptive Convolution

Kang, Di; Dhar, Debarun; Chan, Antoni B.

doi:10.1007/s11263-020-01345-8

Cited by 54 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks have been successfully applied to a wide variety of domains, ranging from speech or visual recognition (Abdel-Hamid et al, 2014;Krizhevsky et al, 2012) to natural language processing (Collobert et al, 2011). Similar ideas of using adaptive or dynamic convolutional filters have been studied before (Lee et al, 2010;Jia et al, 2016;Kang et al, 2017). But most of such works focus on image or video processing.…”

Section: Related Workmentioning

confidence: 89%

Adaptive Convolution for Multi-Relational Learning

Jiang¹,

Wang

2019

Proceedings of the 2019 Conference of the North

126

View full text Add to dashboard Cite

We consider the problem of learning distributed representations for entities and relations of multi-relational data so as to predict missing links therein. Convolutional neural networks have recently shown their superiority for this problem, bringing increased model expressiveness while remaining parameter efficient. Despite the success, previous convolution designs fail to model full interactions between input entities and relations, which potentially limits the performance of link prediction. In this work we introduce ConvR, an adaptive convolutional network designed to maximize entity-relation interactions in a convolutional fashion. ConvR adaptively constructs convolution filters from relation representations, and applies these filters across entity representations to generate convolutional features. As such, ConvR enables rich interactions between entity and relation representations at diverse regions, and all the convolutional features generated will be able to capture such interactions. We evaluate ConvR on multiple benchmark datasets. Experimental results show that: (1) ConvR performs substantially better than competitive baselines in almost all the metrics and on all the datasets; (2) Compared with stateof-the-art convolutional models, ConvR is not only more effective but also more efficient. It offers a 7% increase in MRR and a 6% increase in Hits@10, while saving 12% in parameter storage.

show abstract

Section: Related Workmentioning

confidence: 89%

Adaptive Convolution for Multi-Relational Learning

Jiang¹,

Wang

2019

Proceedings of the 2019 Conference of the North

126

View full text Add to dashboard Cite

show abstract

“…In some areas such as computer vision, the primary goal is to analyze high-dimensional image data with spatial structures [42]. Therefore, using convolutional layers has gained a lot of attention in image processing tasks, where each neuron connects to only a restricted sub-area of the previous layer [43]. This work considers MLP networks because the input parameter space consists of a set of predefined features, eliminating the need to perform feature extraction using Convolutional Neural Networks (CNNs).…”

Section: A Classificationmentioning

confidence: 99%

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Pourkamali-Anaraki

Hariri-Ardebili

2021

IEEE Access

View full text Add to dashboard Cite

Uncertainty quantification in complex engineering problems is challenging because of necessitating large numbers of expensive model evaluations. This paper proposes a two-stage framework for developing accurate machine learning-based surrogate models in structural engineering. The studied numerical model considers aleatory and epistemic uncertainties, i.e., ground motion features and material properties. Our framework's first step trains classification algorithms on the collected data from our numerical model with a disproportionate ratio of observations from two categories, i.e., failed and safe simulations. We investigate the performance of imbalanced learning strategies along with artificial neural networks to achieve high classification accuracy. The second step of our framework aims to estimate three quantities of interest using the same network architecture, comparing our approach with regularized linear regression models. Moreover, we present a new approach to reducing the number of numerical simulations for developing machine learning-based surrogate models with limited training data. This approach employs Gaussian processes as a powerful probabilistic technique, providing an inherent uncertainty measure to determine the quality of estimated response values. Extensive numerical experiments demonstrate the superior performance of neural networks with three hidden layers compared to traditional machine learning algorithms for both classification and regression tasks. Also, empirical investigations corroborate that Gaussian processes enable us to predict the values of missing simulations for reducing the computational cost associated with numerical models. To conclude this work, we present several applications and future research directions. INDEX TERMS Uncertainty, Gaussian processes, neural networks, imbalanced classification, regression.

show abstract

“…In the figure, * means convolution and the reshape layer converts a 1D vector into a 4D tensor of convolution filter weights. It was originally proposed for object detection [21].…”

Section: Emotion Recognition Based On Listener Adaptive Modelmentioning

confidence: 99%

Speech Emotion Recognition Based on Listener Adaptive Models

Ando

Masumura

Sato

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper presents a novel speech emotion recognition scheme that can deal with the individuality of emotion perception. Most conventional methods directly model the majority decision of multiple listener's perceived emotions. However, emotion perception varies with the listener, which means the conventional methods can mismatch the recognition results to human perception. In order to mitigate this problem, we propose a Listener Adaptive (LA) model that reflects emotion recognition criteria of each listener. One-hot listener codes with several adaptation layers are employed in the LA model. The LA model yields the posterior probabilities of the listener-specific perceived emotions. Majority-voted emotion can be also estimated by averaging, in the LA model, the posterior probabilities for all listeners. Experiments on two emotional speech datasets demonstrate that the proposed approach offers improved listener-wise perceived emotion recognition performance in natural speech.

show abstract

Incorporating Side Information by Adaptive Convolution

Cited by 54 publications

References 28 publications

Adaptive Convolution for Multi-Relational Learning

Adaptive Convolution for Multi-Relational Learning

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Speech Emotion Recognition Based on Listener Adaptive Models

Contact Info

Product

Resources

About