Continual Learning: Applications and the Road Forward
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913328448667648 |
|---|---|
| author | Verwimp, Eli Aljundi, Rahaf Ben-David, Shai Bethge, Matthias Cossu, Andrea Gepperth, Alexander Hayes, Tyler L. Hüllermeier, Eyke Kanan, Christopher Kudithipudi, Dhireesha Lampert, Christoph H. Mundt, Martin Pascanu, Razvan Popescu, Adrian Tolias, Andreas S. van de Weijer, Joost Liu, Bing Lomonaco, Vincenzo Tuytelaars, Tinne van de Ven, Gido M. |
| author_facet | Verwimp, Eli Aljundi, Rahaf Ben-David, Shai Bethge, Matthias Cossu, Andrea Gepperth, Alexander Hayes, Tyler L. Hüllermeier, Eyke Kanan, Christopher Kudithipudi, Dhireesha Lampert, Christoph H. Mundt, Martin Pascanu, Razvan Popescu, Adrian Tolias, Andreas S. van de Weijer, Joost Liu, Bing Lomonaco, Vincenzo Tuytelaars, Tinne van de Ven, Gido M. |
| contents | Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask: "Why should one care about continual learning in the first place?". We set the stage by examining recent continual learning papers published at four major machine learning conferences, and show that memory-constrained settings dominate the field. Then, we discuss five open problems in machine learning, and even though they might seem unrelated to continual learning at first sight, we show that continual learning will inevitably be part of their solution. These problems are model editing, personalization and specialization, on-device learning, faster (re-)training and reinforcement learning. Finally, by comparing the desiderata from these unsolved problems and the current assumptions in continual learning, we highlight and discuss four future directions for continual learning research. We hope that this work offers an interesting perspective on the future of continual learning, while displaying its potential value and the paths we have to pursue in order to make it successful. This work is the result of the many discussions the authors had at the Dagstuhl seminar on Deep Continual Learning, in March 2023. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_11908 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Continual Learning: Applications and the Road Forward Verwimp, Eli Aljundi, Rahaf Ben-David, Shai Bethge, Matthias Cossu, Andrea Gepperth, Alexander Hayes, Tyler L. Hüllermeier, Eyke Kanan, Christopher Kudithipudi, Dhireesha Lampert, Christoph H. Mundt, Martin Pascanu, Razvan Popescu, Adrian Tolias, Andreas S. van de Weijer, Joost Liu, Bing Lomonaco, Vincenzo Tuytelaars, Tinne van de Ven, Gido M. Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask: "Why should one care about continual learning in the first place?". We set the stage by examining recent continual learning papers published at four major machine learning conferences, and show that memory-constrained settings dominate the field. Then, we discuss five open problems in machine learning, and even though they might seem unrelated to continual learning at first sight, we show that continual learning will inevitably be part of their solution. These problems are model editing, personalization and specialization, on-device learning, faster (re-)training and reinforcement learning. Finally, by comparing the desiderata from these unsolved problems and the current assumptions in continual learning, we highlight and discuss four future directions for continual learning research. We hope that this work offers an interesting perspective on the future of continual learning, while displaying its potential value and the paths we have to pursue in order to make it successful. This work is the result of the many discussions the authors had at the Dagstuhl seminar on Deep Continual Learning, in March 2023. |
| title | Continual Learning: Applications and the Road Forward |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.11908 |