Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering

• URL: http://arxiv.org/abs/2606.21540v1
• Date: Fri, 19 Jun 2026 15:39:24 GMT
• Title: Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering
• Abstract summary: Graphal networks (GCNs) have demonstrated significant success in complex user-item relationships for collaborative convolution convolution approximation.<n>Due to their reliance on extensive model training, training-free graph filtering (GF) methods have emerged as promising alternative.<n>We propose Mem-GF (Memory-efficient GF), a new GF-based CF method that departs from conventional designs by principally leveraging the structure of Krylov subspaces.
• Score: 15.552528989405978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph convolutional networks (GCNs) have demonstrated significant success in capturing complex user-item relationships for collaborative filtering (CF). However, due to their reliance on extensive model training, training-free graph filtering (GF)-based CF methods have emerged as a promising alternative, offering computational efficiency by smoothing graph signals via matrix operations. In particular, polynomial GF-based approaches demonstrate improved accuracy through their ability to design more expressive and flexible filtering functions. Despite these advantages, existing GF methods suffer from a critical memory bottleneck: they necessitate storing the full item similarity graph, incurring prohibitive memory costs for large-scale datasets, which limits their practical applicability. To tackle this challenge, we propose Mem-GF (Memory-efficient GF), a new GF-based CF method that departs from conventional designs by principally leveraging the structure of Krylov subspaces as a core mechanism for approximating polynomial graph filters without explicitly storing the item similarity graph. We theoretically analyze the minimum Krylov subspace size that guarantees lossless approximation. Through extensive experiments, we demonstrate that Mem-GF achieves up to 5.74$\times$ lower memory usage and 4.38$\times$ speedup in runtime, while consistently exceeding the recommendation accuracy of state-of-the-art GF and GCN-based methods. Mem-GF robustly scales to datasets with tens of millions of interactions, establishing itself as a practically viable and theoretically grounded solution for efficient CF.

Related papers

• Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle [56.92868481531399]
  We propose a non-selfishness principle that prioritizes the collective interference of neighborhood in coarsening.<n>We derive a faster variant NOPE*, which reduces O(dot d) interference evaluation to O(d) based on the local isotropy assumption.<n>Learning on coarsened graphs yields comparable performance to original graphs, and can even show superior performance over LLM-based graph reasoning.
  arXiv  Detail & Related papers  (2026-05-13T05:24:35Z)
• Towards Pre-trained Graph Condensation via Optimal Transport [52.6504753271008]
  Graph condensation aims to distill the original graph into a small-scale graph, mitigating redundancy and accelerating GNN training.<n> conventional GC approaches heavily rely on rigid GNNs and task-specific supervision.<n>Pre-trained Graph Condensation (PreGC) via optimal transport is proposed to transcend the limitations of task- and architecture-dependent GC methods.
  arXiv  Detail & Related papers  (2025-09-18T08:13:24Z)
• Schreier-Coset Graph Propagation [2.0339465062586566]
  This work introduces Schrier-Coset Graph Propagation (SCGP), a group-theoretic augmentation method that enriches node features through Schreier-coset embeddings without altering the input graph topology.<n>SCGP embeds bottleneck-free connectivity patterns into a compact feature space, improving long-range message passing while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-05-15T15:14:02Z)
• Efficient Graph Condensation via Gaussian Process [8.099774846541438]
  Graph condensation reduces the size of large graphs while preserving performance.<n>Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability.<n>This paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation.
  arXiv  Detail & Related papers  (2025-01-05T14:43:07Z)
• GDSG: Graph Diffusion-based Solution Generator for Optimization Problems in MEC Networks [109.17835015018532]
  We present a Graph Diffusion-based Solution Generation (GDSG) method.<n>This approach is designed to work with suboptimal datasets while converging to the optimal solution large probably.<n>We build GDSG as a multi-task diffusion model utilizing a Graph Neural Network (GNN) to acquire the distribution of high-quality solutions.
  arXiv  Detail & Related papers  (2024-12-11T11:13:43Z)
• Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition [49.41718583061147]
  Graph condensation is a data-centric solution to replace the large graph with a small yet informative condensed graph.<n>Existing GC methods suffer from intricate optimization processes, necessitating excessive computing resources and training time.<n>We propose a training-free GC framework termed Class-partitioned Graph Condensation (CGC)<n>CGC condenses the Ogbn-products graph within 30 seconds, achieving a speedup ranging from $102$X to $104$X and increasing accuracy by up to 4.2%.
  arXiv  Detail & Related papers  (2024-05-22T14:57:09Z)
• Turbo-CF: Matrix Decomposition-Free Graph Filtering for Fast Recommendation [9.582288420754152]
  Turbo-CF is a GF-based graph filter that is both training-free and matrix decomposition-free. We demonstrate that Turbo-CF is extremely fast yet accurate, achieving a runtime of less than 1 second on real-world benchmark datasets.
  arXiv  Detail & Related papers  (2024-04-22T14:56:36Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering [96.65234340724237]
  We show the equivalence between some state-of-the-art GNN-based CF models and a traditional 1-layer NRL model based on context encoding. We present Markov Graph Diffusion Collaborative Filtering (MGDCF) to generalize some state-of-the-art GNN-based CF models.
  arXiv  Detail & Related papers  (2022-04-05T17:24:32Z)
• How Powerful is Graph Convolution for Recommendation? [21.850817998277158]
  Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms for collaborative filtering (CF) In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing.
  arXiv  Detail & Related papers  (2021-08-17T11:38:18Z)
• Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions [11.769185588579488]
  We present state-of-the-art performance with lower memory consumption and latency, along with characteristics suited to accelerator implementation. Our proposal uses memory proportional to the number of vertices in the graph, in contrast to competing methods which require memory proportional to the number of edges. We propose aggregator fusion, a technique to enable GNNs to significantly boost their representational power, with only a small increase in latency of 19% over standard sparse matrix multiplication.
  arXiv  Detail & Related papers  (2021-04-03T20:54:36Z)

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.