Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory

Fei Ye, Adrian G. Bors

Introduction

In the field of Continual Learning (CL), models are tasked with learning from a stream of data without forgetting previously acquired knowledge—a challenge known as catastrophic forgetting. Traditional approaches often rely on "task boundaries" or supervised labels to manage memory buffers. However, real-world scenarios are frequently Online Task-Free (OTFCL), where data arrives in small batches without explicit indicators of distribution shifts or available labels.

Overview of the DCM framework for online task-free continual learning, supporting both generative (DDPM) and discriminative (Classifier) tasks.

To address this, researchers have introduced Dynamic Cluster Memory (DCM). This non-parametric system organizes memory into evolving clusters based on the data's inherent structure, enabling both generative and discriminative learning from unlabeled, continuous streams.

The Dynamic Cluster Memory (DCM) Framework

The core of the proposed method is a memory system that treats stored samples as a collection of clusters that can grow or shrink dynamically.

1. Knowledge Discrepancy and Expansion

To determine if a new data point represents a novel concept, DCM employs a Knowledge Discrepancy Measure (KDM). Two variants are proposed: DCM-SE (Square Error) and DCM-JS (Jensen-Shannon divergence). The latter uses a forward diffusion process to make raw data distributions mathematically tractable, providing a robust novelty metric. If a sample's discrepancy exceeds a threshold ($\lambda$), a new memory cluster is created.

Detailed pipeline of the DCM process: sample selection, expansion checking via graph evaluation, and memory pruning.

2. Sample Selection and Pruning

Incoming samples are assigned to the most similar existing cluster prototype. To maintain a fixed memory capacity while preserving diversity, a Memory Pruning Process (MPP) is used. This graph-based evaluation identifies and removes clusters with significant informational overlap, ensuring the memory remains efficient and representative.

3. Integration with Generative Models

DCM is uniquely suited for Denoising Diffusion Probabilistic Models (DDPMs). By providing high-quality "replay" samples from its clusters, it allows generative models to maintain performance across shifting distributions without explicit task labels.

Key Insights and Results

DCM is a "plug-and-play" module that can be integrated into various architectures. Its reliance on cluster prototypes rather than individual samples makes it computationally efficient.

  • Generative Excellence: On the Split CIFAR10 dataset, DCM-JS achieved a Frechet Inception Distance (FID) of 76.58, a significant improvement over the previous state-of-the-art (115.38). It also successfully generated high-resolution ($256 \times 256$) images on CelebA-HQ.
  • Superior Classification: In supervised settings, DCM-JS outperformed established methods like iCARL and CoPE on Split CIFAR100, reaching 26.27% accuracy.
  • Efficiency: The system maintains high performance with fewer stored samples by effectively pruning redundant information.

Conclusion

Dynamic Cluster Memory offers a robust solution for online task-free continual learning. By leveraging non-parametric clustering and diffusion-based distance metrics, it bridges the gap between supervised and unsupervised memory management. Future work may explore more complex graph relations for pruning and extending the framework to other modalities like video and natural language.

Summary updated

Abstract

Online Task-Free Continual Learning (OTFCL) aims to learn novel concepts from streaming data without accessing task information. Most memory-based approaches used in OTFCL are not suitable for unsupervised learning because they require accessing supervised signals to implement their sample selection mechanisms. In this study, we address this issue by proposing a novel memory management approach, namely the Dynamic Cluster Memory (DCM), which builds new memory clusters to capture distribution shifts over time without accessing any supervised signals. DCM introduces a novel memory expansion mechanism based on the knowledge discrepancy criterion, which evaluates the novelty of the incoming data as the signal for the memory expansion, ensuring a compact memory capacity. We also propose a new sample selection approach that automatically stores incoming data samples with similar semantic information in the same memory cluster, while also facilitating the knowledge diversity among memory clusters. Further-more, a novel memory pruning approach is proposed to automatically remove overlapping memory clusters through a graph relation evaluation, ensuring a fixed memory capacity while maintaining the diversity among the samples stored in the memory. The proposed DCM is model-free, plug-and-play, and can be used in both supervised and unsupervised learning without modifications. Empirical results on OTFCL experiments show that the proposed DCM outperforms the state-of-the-art while requiring fewer data samples to be stored. The source code is available at https://github.com/dtuzi123/DCM.
BibTeX
@inproceedings{ye2024online,
  author = {Fei Ye and Adrian G. Bors},
  title = {{Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2024},
  doi = {10.1109/cvpr52733.2024.02476},
}
Figure