Spectral Clustering for Network Coarse-Graining

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

• Greedy Algorithm for Network Coarse-Grainingmethod0.781
  Method to aggregate nodes in complex networks to maximize EI, proposed by Klein & Hoel.
• Coarse Grainingmethod0.756
• Behavior Clusteringconcept0.736
  Grouping similar model behaviors; the unsupervised method surfaces clusters of concerning patterns.
• What coarse-graining strategy generates the maximum effective information?question0.724
  Central optimization problem in CE identification.
• Disjoint neuron clusters for Fourier periodsconcept0.715
  The 28 identified neurons can be partitioned into disjoint clusters each computing a different Fourier period sum
• Noisy Simulation of Sparse Networksconcept0.715
  Mechanism by which superposition works: small neural networks exploit sparsity to approximately simulate much larger sparse networks
• Unsupervised behavior clustering surfaces concerning learned patterns without prior labelsfinding0.713
  Empirical finding: unsupervised clustering reveals problematic patterns without needing labeled data.
• Unsupervised Behavior Clusteringmethod0.710
  Method that clusters behaviors without prior labels, used to surface concerning learned patterns.