Network Classifiers Based on Social Learning
- URL: http://arxiv.org/abs/2010.12306v2
- Date: Fri, 16 Apr 2021 09:43:59 GMT
- Title: Network Classifiers Based on Social Learning
- Authors: Virginia Bordignon, Stefan Vlaski, Vincenzo Matta, Ali H. Sayed
- Abstract summary: We propose a new way of combining independently trained classifiers over space and time.
The proposed architecture is able to improve prediction performance over time with unlabeled data.
We show that this strategy results in consistent learning with high probability, and it yields a robust structure against poorly trained classifiers.
- Score: 71.86764107527812
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work proposes a new way of combining independently trained classifiers
over space and time. Combination over space means that the outputs of spatially
distributed classifiers are aggregated. Combination over time means that the
classifiers respond to streaming data during testing and continue to improve
their performance even during this phase. By doing so, the proposed
architecture is able to improve prediction performance over time with unlabeled
data. Inspired by social learning algorithms, which require prior knowledge of
the observations distribution, we propose a Social Machine Learning (SML)
paradigm that is able to exploit the imperfect models generated during the
learning phase. We show that this strategy results in consistent learning with
high probability, and it yields a robust structure against poorly trained
classifiers. Simulations with an ensemble of feedforward neural networks are
provided to illustrate the theoretical results.
Related papers
- Contrastive Representation Learning for Dynamic Link Prediction in Temporal Networks [1.9389881806157312]
We introduce a self-supervised method for learning representations of temporal networks.
We propose a recurrent message-passing neural network architecture for modeling the information flow over time-respecting paths of temporal networks.
The proposed method is tested on Enron, COLAB, and Facebook datasets.
arXiv Detail & Related papers (2024-08-22T22:50:46Z) - Homological Convolutional Neural Networks [4.615338063719135]
We propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations.
We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models.
arXiv Detail & Related papers (2023-08-26T08:48:51Z) - Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data.
Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
arXiv Detail & Related papers (2023-07-12T16:28:21Z) - Learning from Heterogeneous Data Based on Social Interactions over
Graphs [58.34060409467834]
This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions.
We show that the.
strategy enables the agents to learn consistently under this highly-heterogeneous setting.
We show that the.
strategy enables the agents to learn consistently under this highly-heterogeneous setting.
arXiv Detail & Related papers (2021-12-17T12:47:18Z) - Improving Music Performance Assessment with Contrastive Learning [78.8942067357231]
This study investigates contrastive learning as a potential method to improve existing MPA systems.
We introduce a weighted contrastive loss suitable for regression tasks applied to a convolutional neural network.
Our results show that contrastive-based methods are able to match and exceed SoTA performance for MPA regression tasks.
arXiv Detail & Related papers (2021-08-03T19:24:25Z) - No Fear of Heterogeneity: Classifier Calibration for Federated Learning
with Non-IID Data [78.69828864672978]
A central challenge in training classification models in the real-world federated system is learning with non-IID data.
We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model.
Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
arXiv Detail & Related papers (2021-06-09T12:02:29Z) - PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive
Learning [109.84770951839289]
We present PredRNN, a new recurrent network for learning visual dynamics from historical context.
We show that our approach obtains highly competitive results on three standard datasets.
arXiv Detail & Related papers (2021-03-17T08:28:30Z) - An Ensemble with Shared Representations Based on Convolutional Networks
for Continually Learning Facial Expressions [19.72032908764253]
Semi-supervised learning through ensemble predictions is an efficient strategy to leverage the high exposure of unlabelled facial expressions during human-robot interactions.
Traditional ensemble-based systems are composed of several independent classifiers leading to a high degree of redundancy.
We show that our approach is able to continually learn facial expressions through ensemble predictions using unlabelled samples from different data distributions.
arXiv Detail & Related papers (2021-03-05T20:40:52Z) - Learning from Incomplete Features by Simultaneous Training of Neural
Networks and Sparse Coding [24.3769047873156]
This paper addresses the problem of training a classifier on a dataset with incomplete features.
We assume that different subsets of features (random or structured) are available at each data instance.
A new supervised learning method is developed to train a general classifier, using only a subset of features per sample.
arXiv Detail & Related papers (2020-11-28T02:20:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.