The Oversmoothing Fallacy: A Misguided Narrative in GNN Research
It challenges a key narrative in GNN research, potentially enabling deeper architectures for graph learning tasks.
This paper argues that oversmoothing in Graph Neural Networks (GNNs) has been overstated, showing it is confused with vanishing gradients from transformation and activation, not aggregation, and that skip connections and normalization enable deep GNNs without performance loss.
Oversmoothing has been recognized as a main obstacle to building deep Graph Neural Networks (GNNs), limiting the performance. This position paper argues that the influence of oversmoothing has been overstated and advocates for a further exploration of deep GNN architectures. Given the three core operations of GNNs, aggregation, linear transformation, and non-linear activation, we show that prior studies have mistakenly confused oversmoothing with the vanishing gradient, caused by transformation and activation rather than aggregation. Our finding challenges prior beliefs about oversmoothing being unique to GNNs. Furthermore, we demonstrate that classical solutions such as skip connections and normalization enable the successful stacking of deep GNN layers without performance degradation. Our results clarify misconceptions about oversmoothing and shed new light on the potential of deep GNNs.