Multi-Task Feature Interaction Learning

By Kaixiang Lin, Jianpeng Xu, Inci M. Baytas, Shuiwang Ji, Jiayu Zhou. 2016

33 citations recorded by the source corpus.

One major limitation of linear models is the lack of capability to capture predictive information from interactions between features. While introducing high-order feature interaction terms can overcome this limitation, this approach tremendously increases the model complexity and imposes significant challenges in the learning against overfitting. In this paper, we proposed a novel Multi-Task feature Interaction Learning~(MTIL) framework to exploit the task relatedness from high-order feature interactions, which provides better generalization performance by inductive transfer among tasks via shared representations of feature interactions. We formulate two concrete approaches under this framework and provide efficient algorithms: the shared interaction approach and the embedded interaction approach. The former assumes tasks share the same set of interactions, and the latter assumes feature interactions from multiple tasks come from a shared subspace. We have provided efficient algorithms for solving the two approaches. Extensive empirical studies on both synthetic and real datasets have demonstrated the effectiveness of the proposed framework.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Yu Zhang
3. Xi Yin
4. Xiaoming Liu
5. Mingsheng Long
6. Jianmin Wang
7. Dongrui Wu
8. Sinno Jialin Pan

In Computer Vision and Pattern Recognition

1. Xiaoming Liu
2. Qiang Yang
3. Xi Yin
4. Yu Zhang
5. Dacheng Tao
6. Xiaoou Tang
7. Xiaogang Wang
8. Luc Van Gool

Citations in the corpus

• A Survey on Multi-Task Learning (2017, background): “pairwise interactions between features, two models are proposed in [150] to learn a quadratical function, where the feature interaction”
• Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition (2017, background): “ example, Obozinski et al. [36] propose to penalize the sum of l 2-norm of the blocks of weights associated with each feature across different tasks to encourage similar sparsity patterns. Lin et al. [30] propose to learn higher order feature interaction without limiting to linear model for MTL. Oth”