Aug 2026· Moratuwa Engineering Research Conference· pp. 1235-1240· 0 citations· 26 references
Abstract
Curriculum Learning (CL) orders training samples from easy to hard, but its application to graphs remains limited: existing methods rely on architecture-specific signals such as training loss, or on hand-crafted structural heuristics that do not transfer across datasets. Standard Graph Neural Network (GNN) training sidesteps this entirely, sampling at random and ignoring substantial informational variation across graphs. While pre-defined, generalizable difficulty scores are well established for text and images, no analogue exists for graphs. We propose Tag Entropy, a static, model-agnostic scoring function that measures graph difficulty as the normalized Shannon entropy of node attribute distributions. The same formulation applies to graphs with single discrete tags and to those with high-dimensional categorical features, with the latter handled through a lossless tuple-to-integer compression that preserves joint atom states. Combined with a root-pacing schedule that gradually introduces higher-entropy graphs, the framework requires no pretraining and no domain expertise. Across PROTEINS, MUTAG, NCI1, and OGBG-MOLHIV with GCN, GAT, and GIN backbones, Tag Entropy is competitive with or exceeds twelve baselines. The largest gains appear on architectures most sensitive to ordering: on PROTEINS, GIN improves from 74.11% to 77.86%, and on MUTAG, GAT improves from 69.47% to 73.68%.
While foundation models have revolutionized natural language processing and computer vision by leveraging universal vocabularies, Graph Machine Learning (GML) remains fractured due to the absence of a unified feature and structural representation across diverse domains. Existing works claiming to be Graph Foundation Mo...
Ben Finkelshtein, André Linhares, Petar Veličković et al.· arXiv.org· 1 citation
Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in-context learning (ICL) avoids this by using a single pretrained model to predict unknown node labels directly from labeled context nodes. E...
This paper proposes Curriculum-GraphLLM, a novel graphLLM framework for joint optimization of architectures, structures, and texts for denoised graph neural architecture search to jointly optimize GNN architectures, graph structures, and textual semantics as a unified denoising process during architecture search.
Xin Wang, Haibo Chen, Linxin Xiao et al.· IEEE Transactions on Pattern...· 0 citations
A multimodal model that combines two complementary ideas: a self-supervised method that enables a GNN encoder pretrained on one dataset to operate directly on another dataset with a different node-feature dimensionality, without rebuilding the model or realigning the data is investigated.
Fumiaki Kimino, Ryoma Sato Sokendai, National Institute of Informatics· 1 citation
These findings affirm that neuro symbolic regularization in practice prunes the embedding space of logically invalid relations, yielding a robust and interpretable alternative to fully data driven models.
Ahmed H. Mohammed· Dijlah Journal of Engineerin...· 0 citations
This study introduces a novel memory-augmented self-learning framework that extracts and provides diverse learning sources for adaptive knowledge distillation from the student model itself, resulting in a 2.5-6% increase in accuracy across various benchmark datasets compared to current GNN training and self-distillatio...
Saurabh Sharma, Souvik Chowdhury, Joydeep Chandra· Data mining and knowledge di...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.