v0.2.0.0 Graph Neural Team Formation

• Debiasing reranking algorithms to mitigate the popularity and gender disparities in the neural models' team recommendations based on two alternative notions of fairness: equality of opportunity and demographic parity, , as shown in our colab script

• Gnn-based models added via src/mdl/gnn.py using PyG, where the optimum subset of experts is predicted via link prediction between expert and team nodes in an expert graph, as shown in our colab script

• Seq-to-seq and transformer-bases models added via src/mdl/nmt.py using OpenNMT-py, where the optimum subset of experts is predicted via sequence prediction from sequence of skills to the sequence of experts.

• Temporal training strategy for neural models' training added via src/mdl/tntf.py to capture the evolution of experts' skills and collaboration ties over time, as opposed to randomly shuffled training datasets.

• hydra is integrated for the settings of the steps and hyperparameters of models

• Unit/integration tests of all different configs/settings for all available datasets are added in workflows