CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.
arXiv preprint arXiv:1810.00821 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Neural networks reconstruct classical mutual information and specific entropy from limited projective measurements in the antiferromagnetic quantum Ising model, enabling reconstruction of the phase diagram even for delocalized paramagnetic states.
citing papers explorer
-
Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective
CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.
-
Estimating classical mutual information between quantum subsystems with neural networks
Neural networks reconstruct classical mutual information and specific entropy from limited projective measurements in the antiferromagnetic quantum Ising model, enabling reconstruction of the phase diagram even for delocalized paramagnetic states.