SALE-MLP: Structure Aware Latent Embeddings for GNN to Graph-free MLP Distillation

Authors: Harsh Pal, Sarthak Malik, Rajat Patel, Aakarsh Malhotra

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that SALE-MLP outperforms existing G2M methods across tasks and datasets, achieving 3 4% improvement in node classification for inductive settings while maintaining strong transductive performance.
Researcher Affiliation Industry Harsh Pal , Sarthak Malik , Rajat Patel , Aakarsh Malhotra AI Garage, Mastercard, Gurugram, Haryana, India EMAIL, EMAIL
Pseudocode Yes Algorithm 1 Proposed SALE-MLP
Open Source Code Yes For more details on the implementation and additional results (including other unsupervised structural losses), read the supporting material1. 1https://github.com/ganzagun/SALE-MLP
Open Datasets Yes Datasets: The experimentation utilizes six widely-adopted public benchmark datasets: (Cora, Citeseer, Pubmed) [Sen et al., 2008], (Amazon-Photo, Amazon-Computer) [Feng et al., 2022], and the large-scale graph ogbn-arxiv [Hu et al., 2020].
Dataset Splits Yes Furthermore, for Cora, Citeseer, and Pubmed, we follow splits from [Kipf and Welling, 2022] and for the Amazon dataset, we use splits from [Zhang et al., 2022a] i.e., using 20-shot for training, 30-shot for validation, and remaining for testing. While ogbn-arxiv uses standard splits [Hu et al., 2020].
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models or processor types used for running its experiments. It only mentions inference time without specifying the hardware.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python, PyTorch, CUDA versions) needed to replicate the experiment.
Experiment Setup Yes For SALE-MLP, we perform a grid search for the hyper-parameters below on the validation data: # Hidden layers = {2,3} # Walks = {1,2,5} Walk len = {3,5,10} Pre-train Epochs = {1,2,5,10} λ = {0.0, 0.1, ... , 1.0} α = {1, 1.5, 2, 2.5, 3, 3.5, 4} Hidden layer Dimensionality = {64,128,256}