Rethinking Multi-Label Node Classification: Do Tuned Classic GNNs Suffice?
It challenges the necessity of complex label-aware designs for multi-label node classification, advocating for stronger baseline evaluations in graph learning.
The paper shows that carefully tuned classic GNNs (GCN, SSGConv, GCNII) outperform specialized multi-label methods on 4 out of 5 benchmark datasets, achieving state-of-the-art results in multiple settings.
Multi-label node classification (MLNC) has recently been addressed by increasingly complex label-aware designs that explicitly model node-label interactions and inter-label dependencies.However, it remains unclear whether the advantages of these methods truly stem from their specialized designs, or simply from insufficiently optimized baselines. In this paper, we revisit MLNC from a strong-baseline perspective and investigate whether carefully tuned classic full-graph GNNs can already serve as strong solutions to this task. We systematically study several representative backbones, including GCN, SSGConv, and GCNII, and optimize them using standard yet effective techniques such as normalization, dropout, and residual connections. Experiments on five representative benchmark datasets show that our tuned baselines outperform representative specialized methods on four datasets and achieve state-of-the-art performance in multiple settings. These results indicate that careful tuning of classic backbones is a highly influential but often overlooked factor in MLNC, and highlight the need for more rigorous strong-baseline evaluation in future research on multi-label graph learning.