Chinese Journal of Computers   Full Text
Title	A Manifold Learning-Based Multi-Instance Regression Algorithm
Authors	ZHAN De-Chuan ZHOU Zhi-Hua
Address	(National Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093)
Year	2006
Issue	No.11(1948—1955)
Abstract &   Background	Abstract Multi-instance learning is regarded as a new learning framework. Previous researches mainly focus on multi-instance classification. Recently, multi-instance regression attracts the attention of the machine learning community. Manifold learning attempts to obtain the intrinsic structure of non-linearly distributed data, which can be used in non-linear dimensionality reduction (NLDR). In this paper, a manifold learning-based multi-instance regression algorithm, ManiMIL, is proposed. ManiMIL performs NLDR on the instances in training bags, selects the most diverse dimension that NLDR brings and builds a classifier only on this dimension and then makes the prediction. Experimental results show that the performance of ManiMIL outperforms that of existing multi-instance algorithms such as Citation-kNN. keywords machine learning； multi-instance learning； multi-instance regression； manifold learning background At present, roughly speaking, there are three frameworks for learning from examples. That is, supervised learning, unsupervised learning and reinforcement learning. Multi-instance learning is regarded as a new learning framework. Previous researches mainly focus on multi-instance classification. Recently, multi-instance regression attracts the attention of the machine learning community. Manifold learning attempts to obtain the intrinsic structure of non-linearly distributed data, which can be used in non-linear dimensionality reduction(NLDR). In this paper, a manifold learning-based multi-instance regression algorithm, ManiMIL, is proposed.