Consumable Data via Quantum Communication

Classical data can be copied and re-used for computation, with adverse consequences economically and in terms of data privacy. Motivated by this, we formulate problems in one-way communication complexity where Alice holds some data $x$ and Bob holds $m$ inputs $y_1,... , y_m$. They want to compute $m$ instances of a bipartite relation $R$ on every pair $(x, y_1),\ldots, (x, y_m)$. We call this the asymmetric direct sum question for one-way communication. We give a number of examples where the quantum communication complexity of such problems scales polynomially with $m$, while the classical communication complexity depends at most logarithmically on $m$. Thus, for such problems, data behaves like a consumable resource that is effectively destroyed upon use when the owner stores and transmits it as quantum states, but not when transmitted classically. We show an application to a strategic data-selling game, and discuss other potential economic implications.