Source-linked AI summary
iTAML: An Incremental Task-Agnostic Meta-learning Approach
Jathushan Rajasegaran, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Mubarak Shah
TL;DR
Incremental learning requires models to acquire new tasks without losing prior knowledge. iTAML learns shared meta-parameters, balances old and new information, and automatically predicts and adapts to tasks; experiments report consistent improvements across five classification datasets.
Problem
Class-incremental learning must preserve old knowledge while sequentially learning new class groups, but plasticity, stability, catastrophic forgetting, interference, task information, and replay imbalance remain challenges.
Method
iTAML learns task-agnostic shared parameters with an equilibrium-preserving meta-update, automatically predicts the task, and quickly adapts using task-specific parameters.
Results
iTAML consistently improves performance across ImageNet, CIFAR100, MNIST, SVHN, and MS-Celeb, including a 21.3% gain over RPS-net on CIFAR100 with 10 incremental tasks.
Takeaways & Limitations
The approach provides a generic model that can be rapidly updated for specific tasks while maintaining an equilibrium between old and new task information.
Takeaways & Limitations
The analysis assumes incorrect predictions are uniformly distributed when deriving the probability of predicting the correct task.
Abstract
from arXiv · showhide
Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous meta-learning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively.
1. Introduction
Class-incremental learning must balance retaining old knowledge with learning new class groups under limited access to prior data. iTAML addresses this with task-agnostic meta-learning that learns shared parameters, predicts tasks automatically, and adapts while reducing forgetting and imbalance.
- Incremental learning seeks one model that continually learns new tasks while preserving old knowledge with limited or no access to previous data.
- Class-incremental learning exposes groups of classes sequentially, creating a tension between plasticity for new tasks and stability for old ones.
- iTAML learns a generic meta-model whose shared parameters balance current and old knowledge instead of fitting a single one-size-fits-all model.
- Meta-learning methods such as MAML, FOMAML, and Reptile lack sufficient task adaptation or old-task retention, while task information and replay buffers impose additional constraints.
- iTAML automatically predicts the task, adapts to it, separates generic features from task-specific classifiers, and tunes task-specific parameters separately to reduce imbalance.
2. Related Work
Prior incremental-learning research includes architectural, rehearsal, regularization, and meta-learning strategies. Meta-learning methods aim to learn rapid adaptation, but existing approaches impose restrictions involving gradient alignment, task streams, inference data, or single-sample updates.
- Incremental-learning methods modify architectures, rehearse exemplars or generated samples, or operate algorithmically through regularization and meta-learning.
- Regularization approaches reduce forgetting through distillation, attention preservation, classifier bias correction, synaptic-importance estimates, parameter merging, or Fisher-based constraints.
- Meta-learning aims to train models across tasks so new tasks can be learned quickly with minimal supervision.
- Prior meta-learning approaches align updates or disentangle representations and task heads, but rely on fixed objectives, correlated streams, concurrent inference samples, or single-sample inner-loop updates.
3. Proposed Method
iTAML learns generic parameters that adapt across sequential tasks while separating shared features from task-specific classifiers. Its meta-update combines task-specific models with task-dependent momentum, enabling task identification and rapid class prediction without inference-time gradient updates.
- Core design: iTAML learns shared feature parameters and task-specific classifiers so one generic model can adapt across tasks without requiring task information.The approach is model- and task-agnostic and seeks parameters that work well for new tasks with minor local changes.
- Inner loop: Training samples from current data and exemplar memory are grouped by task into micro-batches, each producing a task-specific model for the outer update.The feature parameters are updated for every task, while each task classifier is updated only on its corresponding micro-batch.
- Outer loop: The outer loop moves the generic model toward the average direction of task-specific updates using a dynamic controller η.This combines the task-specific models rather than optimizing a single task-specific solution.
- Momentum control: η = exp(−βt/T) slows parameter movement as more tasks are observed, balancing adaptation to new tasks with preservation of previous information.The controller is set using a validation-set decay rate β; later-task updates therefore move more slowly than early-task updates.
- Meta-update: Unlike Reptile, iTAML can work with r ≥ 1 inner-loop updates and uses one micro-batch per task to estimate the outer-loop update.The authors motivate this choice by the under-representation of old classes in exemplar-based incremental learning.
- Inference: At inference, iTAML predicts the task from a data continuum, then adapts generic parameters with a small exemplar set to predict classes.Task prediction can reach up to 100% accuracy, while class prediction can be close to joint training without gradient updates after meta-training.
4. Experiments and Results
Experiments evaluate iTAML across incremental-learning benchmarks, meta-learning settings, and ablations. The method consistently outperforms competing approaches, including large gains on CIFAR100 and large-scale datasets.
- Benchmark setup: iTAML is evaluated on MNIST, SVHN, CIFAR100, ImageNet-100, ImageNet-1K, and MS-Celeb-10K incremental-learning benchmarks.The experiments use varied dataset scales, task counts, architectures, and exemplar-memory sizes.
- Meta-learning comparisons: 77.79% average classification accuracy is maintained after 10 CIFAR100 tasks, while task prediction remains above 95% in the task-agnostic setting.The comparison includes FOMAML, Reptile, joint training, and iTAML under task-agnostic, task-aware, and no-inference-update conditions.
- CIFAR100 results: 21.3% is iTAML’s margin over RPS-net when incrementally learning 10 CIFAR100 tasks; gains are 23.6% and 18.2% for 5 and 20 classes, respectively.The experiments report state-of-the-art performance across all three CIFAR100 incremental settings.
- Large-scale results: 19.1% is iTAML’s absolute gain on ImageNet-1K, while it reaches 95.02% accuracy on MS-Celeb-10K with 10,000 classes.It also achieves 89.8% on ImageNet-100, surpassing the current best method by 15.7%.
- Ablation analysis: Increasing the data-continuum size improves task-prediction accuracy by attenuating noise in the average response.The ablations examine continuum size, inner-loop updates, β, and dataset-specific task and class accuracy.
5. Conclusion
iTAML trains a generic model that adapts quickly to specific tasks while preserving an equilibrium between old and new task information. Its task-agnostic design automatically detects the task and improves classification consistently across several datasets.
- iTAML optimizes common parameters across encountered tasks rather than specializing the model to a single task.
- The meta-learning approach rapidly updates a generic model for a specific task while balancing old and new task information.
- iTAML automatically detects the task at inference and updates itself to perform well on the given inputs.
- Experiments show consistent improvements across ImageNet, CIFAR100, MNIST, SVHN and MS-Celeb.
Appendix A.1. iTAML vs Other Meta Algorithms
The appendix formalizes iTAML's inner-loop updates and meta-gradient construction, including a formulation that permits any number of inner-loop updates. It contrasts this with Reptile's requirement for more than one update.
- The inner-loop parameters follow gradient descent on a task loss using learning rate α.
- The meta-gradient is defined from the displacement between initial and updated parameters, following a Reptile-style update rule.
- iTAML permits r ≥ 1 inner-loop updates, whereas Reptile requires r > 1 because r = 1 becomes joint training.
- For task t, the meta-update uses the gradients available from the task sequence.
- iTAML updates shared feature parameters and task-specific classification parameters during each task's inner loop.
Appendix A.2. Additional Results
Additional experiments examine adaptation settings, dataset-specific choices, model size, and optimizer modularity. The results show limited benefit from increasing adaptation epochs and strong performance across small and full backends and multiple optimizers.
- Figure 8 evaluates CIFAR100 classification accuracy with 2 tasks, 2000 exemplar samples, ResNet-18(1/3), and p=20.
- b=1 is used for adaptation because increasing b to 5 does not significantly improve accuracy while increasing time complexity linearly.
- For SVHN, r=4 is retained for the last task because lower data-distribution variance can trap the model at early local minima.
- 69.94% accuracy is achieved with a 0.49M-parameter model, a 13.46% gain over the 77.5M-parameter RPS-net method.
- ResNet-18 reaches 80.27% accuracy, while SGD, Adam and RAdam produce 70.34%, 74.83% and 76.63% accuracy, respectively.