Even if it is possible, it is probably not wise.
Every time a would-be deadlock occurs, you are turning it into a connection that sits around taking up some resources for 50 seconds. With your "heavy concurrency", this might lead to "running out of connections". At that point, no one is getting anything done.
Instead, let's discuss one of your common transactions that sometimes deadlocks. (You can probably catch one via
SHOW ENGINE=INNODB STATUS;.) The may be simple ways to cut down on the frequency of deadlocking and/or speed up the transaction. Or maybe combine multiple transactions into one, thereby diminishing the overhead.
Meanwhile, I assume this is what you are referring to?
----- 2016-09-12 8.0.0 Development Milestone & 2016-09-06 5.7.15 General Availability -- Functionality Added or Changed -- InnoDB -----
A new dynamic configuration option, innodb_deadlock_detect, can be used to disable deadlock detection. On high concurrency systems, deadlock detection can cause a slowdown when numerous threads wait for the same lock. At times, it may be more efficient to disable deadlock detection and rely on the innodb_lock_wait_timeout setting for transaction rollback when a deadlock occurs. (Bug #23477773)