Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Overview of Federated Learning (FL) and data heterogeneity.

More »

Table 1 Expand

Fig 1.

Conventional model training.

More »

Fig 1 Expand

Fig 2.

Collaborative model training (Federated learning).

More »

Fig 2 Expand

Fig 3.

Methodology—Federated learning with different clients.

More »

Fig 3 Expand

Fig 4.

Flowchart.

More »

Fig 4 Expand

Fig 5.

Proposed study—Experimental investigation process.

More »

Fig 5 Expand

Table 2.

Datasets detail.

More »

Table 2 Expand

Fig 6.

Accuracy of IID vs. non-IID (Model: CNN, Clients: 10, Rounds: 50).

More »

Fig 6 Expand

Table 3.

Global accuracy using CNN.

More »

Table 3 Expand

Table 4.

Global accuracy using MLP.

More »

Table 4 Expand

Fig 7.

Accuracy of IID vs. non-IID (Model: MLP, Clients: 10, Rounds: 50).

More »

Fig 7 Expand

Table 5.

Global accuracy with more clients.

More »

Table 5 Expand

Fig 8.

Accuracy of IID vs. non-IID (Model: MLP, Clients 20, Rounds: 50).

More »

Fig 8 Expand

Fig 9.

Accuracy of IID vs. non-IID (Model: MLP, Clients 20, Rounds: 100).

More »

Fig 9 Expand

Table 6.

Global accuracy with more communiation rounds.

More »

Table 6 Expand

Fig 10.

Accuracy of IID vs. non-IID using Dataset-II (Model: MLP, Clients: 10, Rounds: 50).

More »

Fig 10 Expand

Table 7.

Global accuracy using dataset-II.

More »

Table 7 Expand

Table 8.

Global accuracy using Dataset-III.

More »

Table 8 Expand

Fig 11.

Accuracy of IID vs. non-IID using Dataset-III (Model: MLP, Clients: 10, Rounds: 20).

More »

Fig 11 Expand

Fig 12.

Performance decrease comparison with respect to dataset size.

More »

Fig 12 Expand

Table 9.

Comparative analysis.

More »

Table 9 Expand