Skip to yearly menu bar Skip to main content


( events)   Timezone:  
Poster
Fri Jul 13 09:15 AM -- 12:00 PM (PDT) @ Hall B #84
Rectify Heterogeneous Models with Semantic Mapping
Han-Jia Ye · De-Chuan Zhan · Yuan Jiang · Zhi-Hua Zhou
[ PDF [ PDF

On the way to the robust learner for real-world applications, there are still great challenges, including considering unknown environments with limited data. Learnware (Zhou; 2016) describes a novel perspective, and claims that learning models should have reusable and evolvable properties. We propose to Encode Meta InformaTion of features (EMIT), as the model specification for characterizing the changes, which grants the model evolvability to bridge heterogeneous feature spaces. Then, pre-trained models from related tasks can be Reused by our REctiFy via heterOgeneous pRedictor Mapping (REFORM}) framework. In summary, the pre-trained model is adapted to a new environment with different features, through model refining on only a small amount of training data in the current task. Experimental results over both synthetic and real-world tasks with diverse feature configurations validate the effectiveness and practical utility of the proposed framework.