We use the PyTorch toolkit to implement our inpainting network with CICM. The network is optimized by the Adam solver for 400,000 iterations. The initial learning rate is 0.0001, which is linearly decayed during the network training. In our implementation, we use a warm-up strategy to pre-train the backbone network for 50,000 iterations. The encoder of the pre-trained backbone is used to compute the regional features of different images.

Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design.

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption).