{"type":"ScholarlyArticle","title":"SALE-MLP: Structure Aware Latent Embeddings for GNN to Graph-free MLP Distillation","authors":[{"name":"Harsh Pal","slug":"harsh-pal","given":"Harsh","family":"Pal","affiliation":""},{"name":"Sarthak Malik","slug":"sarthak-malik","given":"Sarthak","family":"Malik","affiliation":""},{"name":"Rajat Patel","slug":"rajat-patel","given":"Rajat","family":"Patel","affiliation":""},{"name":"Aakarsh Malhotra","slug":"aakarsh-malhotra","given":"Aakarsh","family":"Malhotra","affiliation":""}],"abstract":"Graph Neural Networks (GNNs), with their ability to effectively handle non-Euclidean data structures, have demonstrated state-of-the-art performance in learning node and graph-level representations. However, GNNs face significant computational overhead due to their message-passing mechanisms, making them impractical for real-time large-scale applications. Recently, Graph-to-MLP (G2M) knowledge distillation has emerged as a promising solution, utilizing MLPs to reduce inference latency. However, existing methods often lack structural awareness (SA), limiting their ability to capture essential graph-specific information. Moreover, some methods require access to large-scale graphs, undermining their scalability. To address these issues, we propose SALE-MLP (Structure-Aware Latent Embeddings for GNN-to-Graph-Free MLP Distillation), a novel graph-free and structure-aware approach that leverages unsupervised structural losses to align the MLP feature space with the underlying graph structure. SALE-MLP does not rely on precomputed GNN embeddings nor require graph during inference, making it efficient for real-world applications. 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.","doi":"10.24963/ijcai.2025/668","url":"https://ijcai.org/proceedings/2025/668","pdf":"https://ijcai.org/proceedings/2025/0668.pdf","markdown":"https://ijcai.org/proceedings/2025/668.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/668","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":668,"pages":{"first":6003,"last":6011},"keywords":["Machine Learning: ML: Deep learning architectures","Machine Learning: ML: Optimization","Machine Learning: ML: Representation learning","Machine Learning: ML: Sequence and graph learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}