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.
We explore and expand the $\textit{Soft Nearest Neighbor Loss}$ to measure the $\textit{entanglement}$ of class manifolds in representation space: i.e., how close pairs of points from the same class are relative to pairs of points from different classes. We demonstrate several use cases of the loss. As an analytical tool, it provides insights into the evolution of class similarity structures during learning. Surprisingly, we find that $\textit{maximizing}$ the entanglement of representations of different classes in the hidden layers is beneficial for discrimination in the final layer, possibly because it encourages representations to identify class-independent similarity structures. Maximizing the soft nearest neighbor loss in the hidden layers leads not only to improved generalization but also to better-calibrated estimates of uncertainty on outlier data. Data that is not from the training distribution can be recognized by observing that in the hidden layers, it has fewer than the normal number of neighbors from the predicted class.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1902.01889")
get_code_for_paper("1902.01889")
have("1902.01889")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1902.01889.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1902.01889)
Connect an agent — have() is free.