Quantifying Representation Reliability in Self-Supervised Learning Models
This addresses the need for reliable representations in downstream tasks, but it is incremental as it builds on existing ensemble and consistency concepts.
The paper tackles the problem of quantifying the reliability of self-supervised learning representations without access to downstream data, proposing an ensemble-based method that uses neighborhood consistency across representation spaces, and demonstrates it achieves high correlation and robust performance in experiments.
Self-supervised learning models extract general-purpose representations from data. Quantifying the reliability of these representations is crucial, as many downstream models rely on them as input for their own tasks. To this end, we introduce a formal definition of representation reliability: the representation for a given test point is considered to be reliable if the downstream models built on top of that representation can consistently generate accurate predictions for that test point. However, accessing downstream data to quantify the representation reliability is often infeasible or restricted due to privacy concerns. We propose an ensemble-based method for estimating the representation reliability without knowing the downstream tasks a priori. Our method is based on the concept of neighborhood consistency across distinct pre-trained representation spaces. The key insight is to find shared neighboring points as anchors to align these representation spaces before comparing them. We demonstrate through comprehensive numerical experiments that our method effectively captures the representation reliability with a high degree of correlation, achieving robust and favorable performance compared with baseline methods.