Multi-dimensional classification via stacked dependency exploitation

Abstract

Multi-dimensional classification (MDC) aims to build classification models for multiple heterogenous class spaces simultaneously, where each class space characterizes the semantics of an object w.r.t. one specific dimension. Modeling dependencies among class spaces plays a key role in solving MDC tasks, where most approaches work by assuming directed acyclic graph (DAG) structure or random chaining structure over class spaces. Different from existing probabilistic strategies, a deterministic strategy named oursfor dependency modeling is proposed in this paper via stacked dependency exploitation. In the first-level, pairwise dependencies are considered which can be modeled more reliably than modeling full dependencies among all class spaces by DAG or chaining structure. In the second-level, the class label of unseen instance w.r.t. each class space is determined by adaptively stacking predictive outputs from first-level pairwise classifiers. Experimental results show that stacked dependency exploitation leads to superior performance against state-of-the-art MDC approaches.