Require:DatasetS = ((x1,y1),..., (xm,ym)) (X { 1}) Afunctionh in HNN can asacascade 2, left column).

Late interaction methods compute representations for the query and corpus graphs separately, and compare these representations using simple similarity functions at the last stage, leading to highly scalable systems. Early interaction methods combine information from both graphs right from the input stages, are usually considerablymoreaccurate,butslower.

O (log log(T)) expected batch complexity. This is achieved through a dynamic batching strategy, which uses the agents estimates to adaptively increase the batch duration.

The number of communication rounds is 100. The total number of clients is 4. A two-layer CNN architecture is used as the backbone model here. The local training batch size is 32. An SGD optimizer with a weight decay rate 5e-4 and a learning rate 0.01 is used. There are 20 clients in total.

FL framework, namely FedICON, to capture invariant knowledge among heterogeneous clients and consistently tune the model to adapt to test data.