Benchmarking GNN Models on Molecular Regression Tasks with CKA-Based Representation Analysis
This work provides systematic benchmarking and fusion insights for researchers in computational chemistry and drug discovery, though it is incremental in nature.
The authors benchmarked four GNN architectures on molecular regression tasks and found that a hierarchical fusion framework (GNN+FP) consistently outperforms standalone GNN models with an RMSE improvement >7%, while CKA analysis revealed that GNN and fingerprint embeddings occupy highly independent latent spaces (CKA ≤0.46).
Molecules are commonly represented as SMILES strings, which can be readily converted to fixed-size molecular fingerprints. These fingerprints serve as feature vectors to train ML/DL models for molecular property prediction tasks in the field of computational chemistry, drug discovery, biochemistry, and materials science. Recent research has demonstrated that SMILES can be used to construct molecular graphs where atoms are nodes ($V$) and bonds are edges ($E$). These graphs can subsequently be used to train geometric DL models like GNN. GNN learns the inherent structural relationships within a molecule rather than depending on fixed-size fingerprints. Although GNN are powerful aggregators, their efficacy on smaller datasets and inductive biases across different architectures is less studied. In our present study, we performed a systematic benchmarking of four different GNN architectures across a diverse domain of datasets (physical chemistry, biological, and analytical). Additionally, we have also implemented a hierarchical fusion (GNN+FP) framework for target prediction. We observed that the fusion framework consistently outperforms or matches the performance of standalone GNN (RMSE improvement > $7\%$) and baseline models. Further, we investigated the representational similarity using centered kernel alignment (CKA) between GNN and fingerprint embeddings and found that they occupy highly independent latent spaces (CKA $\le0.46$). The cross-architectural CKA score suggests a high convergence between isotopic models like GCN, GraphSAGE and GIN (CKA $\geq0.88$), with GAT learning moderately independent representation (CKA $0.55-0.80$).