Loss Adapted Plasticity in Deep Neural Networks to Learn from Data with
Unreliable Sources
- URL: http://arxiv.org/abs/2212.02895v1
- Date: Tue, 6 Dec 2022 11:38:22 GMT
- Title: Loss Adapted Plasticity in Deep Neural Networks to Learn from Data with
Unreliable Sources
- Authors: Alexander Capstick, Francesca Palermo, Payam Barnaghi
- Abstract summary: We show that applying this technique can significantly improve model performance when trained on a mixture of reliable and unreliable data sources.
All code to reproduce this work's experiments and implement the algorithm in the reader's own models is made available.
- Score: 69.6462706723023
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: When data is streaming from multiple sources, conventional training methods
update model weights often assuming the same level of reliability for each
source; that is: a model does not consider data quality of each source during
training. In many applications, sources can have varied levels of noise or
corruption that has negative effects on the learning of a robust deep learning
model. A key issue is that the quality of data or labels for individual sources
is often not available during training and could vary over time. Our solution
to this problem is to consider the mistakes made while training on data
originating from sources and utilise this to create a perceived data quality
for each source. This paper demonstrates a straight-forward and novel technique
that can be applied to any gradient descent optimiser: Update model weights as
a function of the perceived reliability of data sources within a wider data
set. The algorithm controls the plasticity of a given model to weight updates
based on the history of losses from individual data sources. We show that
applying this technique can significantly improve model performance when
trained on a mixture of reliable and unreliable data sources, and maintain
performance when models are trained on data sources that are all considered
reliable. All code to reproduce this work's experiments and implement the
algorithm in the reader's own models is made available.
Related papers
- Diffusion-based Neural Network Weights Generation [85.6725307453325]
We propose an efficient and adaptive transfer learning scheme through dataset-conditioned pretrained weights sampling.
Specifically, we use a latent diffusion model with a variational autoencoder that can reconstruct the neural network weights.
arXiv Detail & Related papers (2024-02-28T08:34:23Z) - Fantastic Gains and Where to Find Them: On the Existence and Prospect of
General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other.
We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
arXiv Detail & Related papers (2023-10-26T17:59:46Z) - RLBoost: Boosting Supervised Models using Deep Reinforcement Learning [0.0]
We present RLBoost, an algorithm that uses deep reinforcement learning strategies to evaluate a particular dataset and obtain a model capable of estimating the quality of any new data.
The results of the article show that this model obtains better and more stable results than other state-of-the-art algorithms such as LOO, DataShapley or DVRL.
arXiv Detail & Related papers (2023-05-23T14:38:33Z) - Analyzing Effects of Fake Training Data on the Performance of Deep
Learning Systems [0.0]
Deep learning models frequently suffer from various problems such as class imbalance and lack of robustness to distribution shift.
With the advent of Generative Adversarial Networks (GANs) it is now possible to generate high-quality synthetic data.
We analyze the effect that various quantities of synthetic data, when mixed with original data, can have on a model's robustness to out-of-distribution data and the general quality of predictions.
arXiv Detail & Related papers (2023-03-02T13:53:22Z) - Probabilistic Neural Data Fusion for Learning from an Arbitrary Number
of Multi-fidelity Data Sets [0.0]
In this paper, we employ neural networks (NNs) for data fusion in scenarios where data is very scarce.
We introduce a unique NN architecture that converts MF modeling into a nonlinear manifold learning problem.
Our approach provides a high predictive power while quantifying various sources uncertainties.
arXiv Detail & Related papers (2023-01-30T20:27:55Z) - Unsupervised Audio Source Separation Using Differentiable Parametric
Source Models [8.80867379881193]
We propose an unsupervised model-based deep learning approach to musical source separation.
A neural network is trained to reconstruct the observed mixture as a sum of the sources.
The experimental evaluation on a vocal ensemble separation task shows that the proposed method outperforms learning-free methods.
arXiv Detail & Related papers (2022-01-24T11:05:30Z) - Deep Transfer Learning for Multi-source Entity Linkage via Domain
Adaptation [63.24594955429465]
Multi-source entity linkage is critical in high-impact applications such as data cleaning and user stitching.
AdaMEL is a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage.
Our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning.
arXiv Detail & Related papers (2021-10-27T15:20:41Z) - Hidden Biases in Unreliable News Detection Datasets [60.71991809782698]
We show that selection bias during data collection leads to undesired artifacts in the datasets.
We observed a significant drop (>10%) in accuracy for all models tested in a clean split with no train/test source overlap.
We suggest future dataset creation include a simple model as a difficulty/bias probe and future model development use a clean non-overlapping site and date split.
arXiv Detail & Related papers (2021-04-20T17:16:41Z) - Unsupervised Multi-source Domain Adaptation Without Access to Source
Data [58.551861130011886]
Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain.
We propose a novel and efficient algorithm which automatically combines the source models with suitable weights in such a way that it performs at least as good as the best source model.
arXiv Detail & Related papers (2021-04-05T10:45:12Z)
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.