Progressive Reasoning by Module Composition
share
Humans learn to solve tasks of increasing complexity by building on top of previously acquired knowledge. Typically, there exists a natural progression in the tasks that we learn - most do not require completely independent solutions, but can be broken down into simpler subtasks. We propose to represent a solver for each task as a neural module that calls existing modules (solvers for simpler tasks) in a program-like manner. Lower modules are a black box to the calling module, and communicate only via a query and an output. Thus, a module for a new task learns to query existing modules and composes their outputs in order to produce its own output. Each module also contains a residual component that learns to solve aspects of the new task that lower modules cannot solve. Our model effectively combines previous skill-sets, does not suffer from forgetting, and is fully differentiable. We test our model in learning a set of visual reasoning tasks, and demonstrate state-of-the-art performance in Visual Question Answering, the highest-level task in our task set. By evaluating the reasoning process using non-expert human judges, we show that our model is more interpretable than an attention-based baseline.
READ FULL TEXT