They're popular enough that we'd penalize a substantial number of users.
Could you add some additional check if that domain is used? (Possibly with browser fingerprinting, or other req fingerprinting)
Possibly something even that just wastes a little time and makes them know you're aware of the behaviour.
Does the email address has a pattern? I faced similar registration attack, but the email address had pattern, I blocked them in code but gave a success response and the attack went away.