Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding

Authors:
Rosemary Ke MILA, University of Montreal
Anirudh Goyal ALIAS PARTH GOYAL Université de Montréal
Olexa Bilaniuk University of Montreal
Jonathan Binas MILA, Montreal
Mike Mozer Google Brain / U. Colorado
Chris Pal MILA, Polytechnique Montréal, Element AI
Yoshua Bengio U. Montreal

Introduction:

Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past.However, humans are often reminded of past memories or mental states which are associated with the current mental state.The authors consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state.

Abstract:

Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most common method for training recurrent neural networks, back-propagation through time (BPTT), requires credit information to be propagated backwards through every single step of the forward computation, potentially over thousands or millions of time steps.This becomes computationally expensive or even infeasible when used with long sequences. Importantly, biological brains are unlikely to perform such detailed reverse replay over very long sequences of internal states (consider days, months, or years.) However, humans are often reminded of past memories or mental states which are associated with the current mental state.We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state. Based on this principle, we study a novel algorithm which only back-propagates through a few of these temporal skip connections, realized by a learned attention mechanism that associates current states with relevant past states. We demonstrate in experiments that our method matches or outperforms regular BPTT and truncated BPTT in tasks involving particularly long-term dependencies, but without requiring the biologically implausible backward replay through the whole history of states. Additionally, we demonstrate that the proposed method transfers to longer sequences significantly better than LSTMs trained with BPTT and LSTMs trained with full self-attention.

You may want to know: