Skip to main content

View full-text article in PMC

. 2022 Jun 2;3(6):100521. doi: 10.1016/j.patter.2022.100521

Table 3.

Performance for federated molecular classification

Dataset	α	Centralized training		Federated learning
Dataset	α	MolNet^a	FedChem^a_ours	FedAvg	FedProx	MOON	FedFocal_ours	FedVAT_ours	FLIT_ours	FLIT+_ours
Tox21 $⇑$	0.1	0.829	0.8182	0.7705	0.7732	0.7331	0.7696	0.7733	0.7711	0.7802^b
	0.5			0.7811	0.7774	0.7461	0.7812	0.7787	0.7825	0.7870^b
	1			0.7770	0.7775	0.7457	0.7881^b	0.7706	0.7748	0.7806
SIDER $⇑$	0.1	0.638	0.6260	0.6029	0.6056^b	0.5885	0.6016	0.6027	0.6035	0.6038
	0.5			0.6011	0.5931	0.5966	0.6086	0.5981	0.6096	0.6146^b
	1			0.6011	0.6023	0.5901	0.6003	0.6053	0.6072	0.6174^b
ClinTox $⇑$	0.1	0.832	0.8903	0.7491	0.7540	0.7892^b	0.7789^b	0.7581	0.7761	0.7775
	0.5			0.7521	0.7423	0.7917^b	0.7770	0.7614	0.7888^b	0.7852
	1			0.7784	0.7791	0.8001	0.8036^b	0.7743	0.7849	0.7993
BBBP $⇑$	0.1	0.690	0.8674	0.8361	0.8610	0.8737^b	0.8550	0.8673^b	0.8666	0.8663
	0.5			0.8594	0.8879^b	0.8865	0.8726	0.8641	0.8671	0.8774
	1			0.8453	0.8557^b	0.8487	0.8378	0.8386	0.8515	0.8515
BACE $⇑$	0.1	0.806	0.8834	0.8203	0.8328	0.8373	0.8253	0.8166	0.8242	0.8467^b
	0.5			0.8212	0.8398	0.8285	0.8332	0.8417	0.8516	0.8667^b
	1			0.8486	0.8408	0.8561	0.8497	0.8578^b	0.8497	0.8561

$⇓, ⇑$ indicate if lower or higher numbers are better.

^a

Results are obtained with centralized training.

^b

Best federated-learning results.