We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of the model in general. We specifically perform a controlled study on the effect of random seeds on the behaviour of attention, gradient-based and surrogate model based (LIME) interpretations. Our analysis suggests that random seeds can adversely affect the consistency of models resulting in counterfactual interpretations. We propose a technique called Aggressive Stochastic Weight Averaging (ASWA)and an extension called Norm-filtered Aggressive Stochastic Weight Averaging (NASWA) which improves the stability of models over random seeds. With our ASWA and NASWA based optimization, we are able to improve the robustness of the original model, on average reducing the standard deviation of the model's performance by 72%.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1909.10447")
get_code_for_paper("1909.10447")
have("1909.10447")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1909.10447.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1909.10447)
Connect an agent — have() is free.