Causal Representation Learning (CRL)

Schölkopf et al.'s framework combining representation learning with causal inference.

Neighborhood — ranked by edge-count

claim

artifact

Yuan 2023 Emergence and Causality in Complex Systems: A Survey
mentions
This review paper surveys quantitative theories of causal emergence and their connections to machine learning.

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.

Causal emergence predictive of final reward early in RL training across multiple algorithms, architectures, and environments.finding0.780
Empirical result: CE measurements correlate with and predict learning performance in RL agents.
in-context learning (ICL)concept0.776
Test-time adaptation from prompt or retrieved context with no parameter updates.
Causal Intervention on Representationsconcept0.773
The use of interventions (rather than correlations) to establish a causal link between representation geometry and behavioral geometry.
Reinforcement learning (RL)concept0.766
Machine learning paradigm where agents learn to maximize cumulative reward through interaction.
Causal emergence provides new perspectives for causal representation learning, interpreting latent variables as emergent causalities.claim0.760
Cross-fertilization claim made in discussion.
In-Context Learning of Representations (Park et al. 2025)framework0.760
Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
causal shaping of behavior by representation geometryconcept0.755
Central question: does geometry in activation space causally determine behavior?
Representational dynamics of causal emergence align with reward improvement in most tasks.finding0.746
The trajectory of causal emergence through training mirrors the reward improvement curve across the majority of tested environments.