Strategic Representation
This addresses the issue of manipulation in human-machine interactions for users relying on machine-generated information, presenting an incremental extension of strategic classification by reversing the roles.
The paper tackles the problem of users making decisions based on representations that may be strategically manipulated by machines, formalizing it as a learning problem where the user learns first and the system responds with truthful but incomplete representations. The main result is a learning algorithm that minimizes error despite these strategic representations, with theoretical analysis exploring the trade-off between learning effort and susceptibility to manipulation.
Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good choices based on strategic representations? We formalize this as a learning problem, and pursue algorithms for decision-making that are robust to manipulation. In our main setting of interest, the system represents attributes of an item to the user, who then decides whether or not to consume. We model this interaction through the lens of strategic classification (Hardt et al. 2016), reversed: the user, who learns, plays first; and the system, which responds, plays second. The system must respond with representations that reveal `nothing but the truth' but need not reveal the entire truth. Thus, the user faces the problem of learning set functions under strategic subset selection, which presents distinct algorithmic and statistical challenges. Our main result is a learning algorithm that minimizes error despite strategic representations, and our theoretical analysis sheds light on the trade-off between learning effort and susceptibility to manipulation.