PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs
Not on the map. Why?
Abstract (arXiv)
Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbnproducts graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this paper, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached into each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven largescale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN can be easily combined with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 68 references that are in the map. First posted on arXiv 14 Oct 2024.
Builds on
35 of 68 references.
References · 35
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
- 2019Strategies for Pre-training Graph Neural Networkscited by 964
- 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
- 2020Simple and Deep Graph Convolutional Networkscited by 857
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
- 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
23 more
- 2019Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networkscited by 177
- 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
- 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
- 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
- 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
- 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
- 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
- 2023On the Connection Between MPNN and Graph Transformercited by 60
- 2022BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Samplingcited by 43
- 2019InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Predictioncited by 39
- 2021VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantizationcited by 39
- 2022CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender Systemcited by 38
- 2023HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networkscited by 32
- 2020Bandit Samplers for Training Graph Neural Networkscited by 30
- 2023LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergencecited by 26
- 2022Layer-Neighbor Sampling -- Defusing Neighborhood Explosion in GNNscited by 19
- 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
- 2023Improving Recommendation Fairness via Data Augmentationcited by 18
- 2022Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embeddingcited by 9
- 2022Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networkscited by 5
- 2024Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Datacited by 5
- 2022Two-level Graph Neural Networkcited by 4
- 2023Transition Propagation Graph Neural Networks for Temporal Networkscited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.