StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure

This work presents StrAE: a Structured Autoencoder framework that through strict adherence to explicit structure, and use of a novel contrastive objective over tree-structured representations, enables effective learning of multi-level representations.

Data and Resources

Cite this as

Mattia Opper, Victor Prokhorov, N. Siddharth (2024). Dataset: StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure. https://doi.org/10.57702/v6jtmjmg

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Mattia Opper
More Authors
Victor Prokhorov
N. Siddharth