Topology-aware Embedding Memory for Continual Learning on Expanding Networks

• URL: http://arxiv.org/abs/2401.13200v3
• Date: Sun, 30 Jun 2024 04:40:35 GMT
• Title: Topology-aware Embedding Memory for Continual Learning on Expanding Networks
• Authors: Xikun Zhang, Dongjin Song, Yixin Chen, Dacheng Tao,
• Abstract summary: We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
• Score: 63.35819388164267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Memory replay based techniques have shown great success for continual learning with incrementally accumulated Euclidean data. Directly applying them to continually expanding networks, however, leads to the potential memory explosion problem due to the need to buffer representative nodes and their associated topological neighborhood structures. To this end, we systematically analyze the key challenges in the memory explosion problem, and present a general framework, \textit{i.e.}, Parameter Decoupled Graph Neural Networks (PDGNNs) with Topology-aware Embedding Memory (TEM), to tackle this issue. The proposed framework not only reduces the memory space complexity from $\mathcal{O}(nd^L)$ to $\mathcal{O}(n)$~\footnote{$n$: memory budget, $d$: average node degree, $L$: the radius of the GNN receptive field}, but also fully utilizes the topological information for memory replay. Specifically, PDGNNs decouple trainable parameters from the computation ego-subnetwork via \textit{Topology-aware Embeddings} (TEs), which compress ego-subnetworks into compact vectors (\textit{i.e.}, TEs) to reduce the memory consumption. Based on this framework, we discover a unique \textit{pseudo-training effect} in continual learning on expanding networks and this effect motivates us to develop a novel \textit{coverage maximization sampling} strategy that can enhance the performance with a tight memory budget. Thorough empirical studies demonstrate that, by tackling the memory explosion problem and incorporating topological information into memory replay, PDGNNs with TEM significantly outperform state-of-the-art techniques, especially in the challenging class-incremental setting.

Related papers

• Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets [3.0894823679470087]
  This paper introduces the Multi-Stage Folding and Unshared Masks methods to expand the search space in terms of both architecture and parameters. By achieving high sparsity, competitive performance, and high memory efficiency with up to 98.7% reduction, it demonstrates suitability for energy-efficient graph processing.
  arXiv  Detail & Related papers  (2023-12-06T02:16:44Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Towards Zero Memory Footprint Spiking Neural Network Training [7.4331790419913455]
  Spiking Neural Networks (SNNs) process information using discrete-time events known as spikes rather than continuous values. In this paper, we introduce an innovative framework characterized by a remarkably low memory footprint. Our design is able to achieve a $mathbf58.65times$ reduction in memory usage compared to the current SNN node.
  arXiv  Detail & Related papers  (2023-08-16T19:49:24Z)
• Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations [4.07484910093752]
  Pruning-at-Initialization (PaI) algorithms provide Sparse Networks (SNNs) which are computationally more efficient than their dense counterparts, and try to avoid performance degradation. While much emphasis has been directed towards emphhow to prune, we still do not know emphwhat topological metrics of the SNNs characterize emphgood performance. We design a comprehensive topological analysis for SNNs with both linear and convolutional layers, via (i) a new input-aware Multipartite Graph (MGE) for SNNs and
  arXiv  Detail & Related papers  (2023-05-26T12:45:58Z)
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning [72.80896338009579]
  We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs. We propose a generic patch-by-patch inference scheduling, which significantly cuts down the peak memory. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2.
  arXiv  Detail & Related papers  (2021-10-28T17:58:45Z)
• GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings [51.82434518719011]
  GNNAutoScale (GAS) is a framework for scaling arbitrary message-passing GNNs to large graphs. Gas prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations. Gas reaches state-of-the-art performance on large-scale graphs.
  arXiv  Detail & Related papers  (2021-06-10T09:26:56Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Robust High-dimensional Memory-augmented Neural Networks [13.82206983716435]
  Memory-augmented neural networks enhance neural networks with an explicit memory to overcome these issues. Access to this explicit memory occurs via soft read and write operations involving every individual memory entry. We propose a robust architecture that employs a computational memory unit as the explicit memory performing analog in-memory computation on high-dimensional (HD) vectors.
  arXiv  Detail & Related papers  (2020-10-05T12:01:56Z)
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning [56.83172249278467]
  We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces. We train and validate our approach directly on the Intel NNP-I chip for inference. We additionally achieve 28-78% speed-up compared to the native NNP-I compiler on all three workloads.
  arXiv  Detail & Related papers  (2020-07-14T18:50:12Z)

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.