A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913508753408000 |
|---|---|
| author | Yu, Xingtong Fang, Yuan Liu, Zemin Wu, Yuxia Wen, Zhihao Bo, Jianyuan Zhang, Xinming Hoi, Steven C. H. |
| author_facet | Yu, Xingtong Fang, Yuan Liu, Zemin Wu, Yuxia Wen, Zhihao Bo, Jianyuan Zhang, Xinming Hoi, Steven C. H. |
| contents | Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This constraint has spurred the emergence of few-shot learning on graphs, where only a few labels are available for each task. Given the extensive literature in this field, this survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions. We systematically categorize existing studies based on two major taxonomies: (1) Problem taxonomy, which explores different types of data scarcity problems and their applications, and (2) Technique taxonomy, which details key strategies for addressing these data-scarce few-shot problems. The techniques can be broadly categorized into meta-learning, pre-training, and hybrid approaches, with a finer-grained classification in each category to aid readers in their method selection process. Within each category, we analyze the relationships among these methods and compare their strengths and limitations. Finally, we outline prospective directions for few-shot learning on graphs to catalyze continued innovation in this field. The website for this survey can be accessed by \url{https://github.com/smufang/fewshotgraph}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01440 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning Yu, Xingtong Fang, Yuan Liu, Zemin Wu, Yuxia Wen, Zhihao Bo, Jianyuan Zhang, Xinming Hoi, Steven C. H. Machine Learning Artificial Intelligence Social and Information Networks Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This constraint has spurred the emergence of few-shot learning on graphs, where only a few labels are available for each task. Given the extensive literature in this field, this survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions. We systematically categorize existing studies based on two major taxonomies: (1) Problem taxonomy, which explores different types of data scarcity problems and their applications, and (2) Technique taxonomy, which details key strategies for addressing these data-scarce few-shot problems. The techniques can be broadly categorized into meta-learning, pre-training, and hybrid approaches, with a finer-grained classification in each category to aid readers in their method selection process. Within each category, we analyze the relationships among these methods and compare their strengths and limitations. Finally, we outline prospective directions for few-shot learning on graphs to catalyze continued innovation in this field. The website for this survey can be accessed by \url{https://github.com/smufang/fewshotgraph}. |
| title | A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2402.01440 |