Open-World Continual Learning: Unifying Novelty Detection and Continual
Learning
- URL: http://arxiv.org/abs/2304.10038v1
- Date: Thu, 20 Apr 2023 01:32:32 GMT
- Title: Open-World Continual Learning: Unifying Novelty Detection and Continual
Learning
- Authors: Gyuhak Kim, Changnan Xiao, Tatsuya Konishi, Zixuan Ke, Bing Liu
- Abstract summary: This paper theoretically proves that OOD detection actually is necessary for CIL.
A good CIL algorithm based on our theory can naturally be used in open world learning.
New CIL methods are also designed, which outperform strong baselines in terms of CIL accuracy and its continual OOD detection by a large margin.
- Score: 13.186315474669287
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As AI agents are increasingly used in the real open world with unknowns or
novelties, they need the ability to (1) recognize objects that (i) they have
learned and (ii) detect items that they have not seen or learned before, and
(2) learn the new items incrementally to become more and more knowledgeable and
powerful. (1) is called novelty detection or out-of-distribution (OOD)
detection and (2) is called class incremental learning (CIL), which is a
setting of continual learning (CL). In existing research, OOD detection and CIL
are regarded as two completely different problems. This paper theoretically
proves that OOD detection actually is necessary for CIL. We first show that CIL
can be decomposed into two sub-problems: within-task prediction (WP) and
task-id prediction (TP). We then prove that TP is correlated with OOD
detection. The key theoretical result is that regardless of whether WP and OOD
detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good
WP and good OOD detection are necessary and sufficient conditions for good CIL,
which unifies novelty or OOD detection and continual learning (CIL, in
particular). A good CIL algorithm based on our theory can naturally be used in
open world learning, which is able to perform both novelty/OOD detection and
continual learning. Based on the theoretical result, new CIL methods are also
designed, which outperform strong baselines in terms of CIL accuracy and its
continual OOD detection by a large margin.
Related papers
- On the Learnability of Out-of-distribution Detection [46.9442031620796]
This paper investigates the probably approximately correct (PAC) learning theory of OOD detection.
We prove several impossibility theorems for the learnability of OOD detection under some scenarios.
We then give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
arXiv Detail & Related papers (2024-04-07T08:17:48Z) - How Does Unlabeled Data Provably Help Out-of-Distribution Detection? [63.41681272937562]
Unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and out-of-distribution (OOD) data.
This paper introduces a new learning framework SAL (Separate And Learn) that offers both strong theoretical guarantees and empirical effectiveness.
arXiv Detail & Related papers (2024-02-05T20:36:33Z) - Exploring Large Language Models for Multi-Modal Out-of-Distribution
Detection [67.68030805755679]
Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class.
In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
arXiv Detail & Related papers (2023-10-12T04:14:28Z) - Feed Two Birds with One Scone: Exploiting Wild Data for Both
Out-of-Distribution Generalization and Detection [31.68755583314898]
We propose a margin-based learning framework that exploits freely available unlabeled data in the wild.
We show both empirically and theoretically that the proposed margin constraint is the key to achieving both OOD generalization and detection.
arXiv Detail & Related papers (2023-06-15T14:32:35Z) - Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is
All You Need [52.88953913542445]
We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly.
We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
arXiv Detail & Related papers (2023-02-06T08:24:41Z) - A Theoretical Study on Solving Continual Learning [13.186315474669287]
This study shows that the CIL problem can be decomposed into two sub-problems: Within-task Prediction (WP) and Task-id Prediction (TP)
It further proves that TP is correlated with out-of-distribution (OOD) detection, which connects CIL and OOD detection.
The key conclusion of this study is that regardless of whether WP and TP or OOD detection are defined explicitly or implicitly by a CIL algorithm, good WP and good TP or OOD detection are necessary and sufficient for good CIL performances.
arXiv Detail & Related papers (2022-11-04T17:45:55Z) - Is Out-of-Distribution Detection Learnable? [45.377641783085046]
We investigate the probably approximately correct (PAC) learning theory of OOD detection.
We prove several impossibility theorems for the learnability of OOD detection under some scenarios.
We then give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
arXiv Detail & Related papers (2022-10-26T13:35:19Z) - Generalized Out-of-Distribution Detection: A Survey [83.0449593806175]
Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems.
Several other problems, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD) are closely related to OOD detection.
We first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems.
arXiv Detail & Related papers (2021-10-21T17:59:41Z) - DOODLER: Determining Out-Of-Distribution Likelihood from Encoder
Reconstructions [6.577622354490276]
This paper introduces and examines a novel methodology, DOODLER, for Out-Of-Distribution Detection.
By training a Variational Auto-Encoder on the same data as another Deep Learning model, the VAE learns to accurately reconstruct In-Distribution (ID) inputs, but not to reconstruct OOD inputs.
Unlike other work in the area, DOODLER requires only very weak assumptions about the existence of an OOD dataset, allowing for more realistic application.
arXiv Detail & Related papers (2021-09-27T14:54:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.