Geodesy

Benchmark (surveying)

Linguistics

Engineering

Philosophy

Transfer of learning

Similarity (geometry)

Systems engineering

Pedagogy

Knowledge transfer

Economics

Set (abstract data type)

Labeled data

Data mining

Parallel computing

Computer science

Lifelong learning

Code (set theory)

Negative transfer

Geology

Oceanography

Transfer (computing)

Psychology

Task (project management)

Source code

Mathematics

Management

Geography

Image (mathematics)

First language

Domain (mathematical analysis)

Mathematical analysis

Artificial intelligence

Geometry

Information retrieval

Point (geometry)

Programming language

Knowledge management

Machine learning

Baseline (sea)

Annotation

IEEE/CAA Journal of Automatica Sinica

Transfer learning (TL) utilizes data or knowledge from one or more source domains to facilitate the learning in a target domain. It is particularly useful when the target domain has very few or no labeled data, due to annotation expense, privacy concerns, etc. Unfortunately, the effectiveness of TL is not always guaranteed. Negative transfer (NT), i.e., leveraging source domain data/knowledge undesirably reduces the learning performance in the target domain, has been a long-standing and challenging problem in TL. Various approaches have been proposed in the literature to handle it. However, there does not exist a systematic survey on the formulation of NT, the factors leading to NT, and the algorithms that mitigate NT. This paper fills this gap, by first introducing the definition of NT and its factors, then reviewing about fifty representative approaches for overcoming NT, according to four categories: secure transfer, domain similarity estimation, distant transfer, and NT mitigation. NT in related fields, e.g., multi-task learning, lifelong learning, and adversarial attacks, are also discussed.

A Survey on Negative Transfer