concept
active
concept:masked-autoencoders

Masked Autoencoders

Self-supervised learning method that optimizes reconstruction tasks; included in the paper's analysis as a multi-task objective

Neighborhood — ranked by edge-count

Hypotheses (1)

hypothesis
  • Argues that there are fewer representations competent for N tasks than M<N tasks, so more general models have a smaller solution space

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Autoencoderconcept0.838
    Neural network architecture that learns compressed representations; SOHMs are functionally equivalent.
  • Deep Autoencoderframework0.803
  • Deep Auto Encoderframework0.790
  • Method used alongside covariance pooling for the Gene Ontology prediction task; produces embeddings without large labeled datasets.
  • Sparse Autoencoderframework0.770
    Interpretability framework used to decompose layer-40 activations into sparse feature sets for studying emotional alignment and persistence
  • Core unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained with RL.
  • An unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained jointly with RL.
  • Transcodersmethod0.735
    Decomposition method for activations; VPD is compared against transcoders in sparsity-reconstruction tradeoff.