Abstract
Artificial neural networks can acquire new capabilities but often damage existing ones when they continue to learn. This stability-plasticity problem has motivated replay, regularization and constrained-update methods, yet it remains unclear whether a property of incoming learning itself determines what can be retained without disrupting protected behaviour. Here we show that functional compatibility, the extent to which new learning can coexist with behaviour that must be preserved, is a causal determinant of persistent learning. To our knowledge, this is the first controlled causal demonstration in which compatibility is deliberately changed from matched neural states and persistent learning is measured under a common retention requirement. The effect generalizes across independent learning directions, convolutional and transformer architectures, vision and text, and additional seeds. Learning rules differ in how efficiently they exploit available compatibility, while retention constraints limit how much can be stored. At larger finite updates, nonlinear geometry changes the available learning opportunity and ultimately prevents the matched compatibility continuum from being realized. These results establish functional compatibility as an experimentally controllable principle of persistent neural learning, shifting the problem from preventing forgetting towards identifying which components of new learning can safely become permanent.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22462
