Advocacy Learning: Learning through Competition and Class-Conditional Representations
Authors: Ian Fox, Jenna Wiens
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our proposed advocacy learning approach across a variety of tasks and compare against a series of different baselines. In this section, we explain each baseline and provide implementation details. ... We begin by examining the performance of advocacy learning across three image datasets, analyzing when and how advocacy learning impacts performance. We then present performance on a significant real-world medical dataset and modified datasets designed to highlight the effects of competition and deception in learning. |
| Researcher Affiliation | Academia | Ian Fox and Jenna Wiens Department of Computer Science and Engineering, University of Michigan, Ann Arbor, USA {ifox, wiensj}@umich.edu |
| Pseudocode | Yes | Algorithm 1: Advocacy Learning Algorithm |
| Open Source Code | Yes | Our specific model architecture (number of layers, filters, etc.) is available via our public code release1. 1https://github.com/igfox/advocacy-learning |
| Open Datasets | Yes | We begin by examining the performance of our Advocacy Net variants and baselines on two publicly available image classification datasets: MNIST and Fashion-MNIST [Xiao et al., 2017]. ... We also examined performance on a more challenging image classification problem, CIFAR-10. ... We applied advocacy learning to a large electronic health record (EHR) dataset, MIMIC III [Johnson et al., 2016]. |
| Dataset Splits | Yes | We split off 10% of our training data to use as a validation set for early stopping. We cease training when validation loss fails to improve over 10 epochs. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments, such as GPU or CPU models, memory specifications, or cloud instance types. It only mentions the software used for implementation. |
| Software Dependencies | No | The paper mentions 'Py Torch [Adam et al., 2017]' and 'Adam [Kingma and Ba, 2014]' but does not specify exact version numbers for PyTorch or any other software dependencies required for replication. |
| Experiment Setup | Yes | We implement our models using Py Torch [Adam et al., 2017]. ... We optimize the network weights using Adam [Kingma and Ba, 2014] with a learning rate of 10 4, and use Dropout and batch normalization to prevent overfitting. We split off 10% of our training data to use as a validation set for early stopping. We cease training when validation loss fails to improve over 10 epochs. ... We regularize the attention maps by adding a penalty proportional to the L1-norm of the map to encourage sparsity consistent with common notions of attention. Parameters were initialized using the default Py Torch method. |