silab4/gnn-rel4593-graphsemcom2

GraphSemCom GNN (rel4593)

This repo contains:

• —encoder_best.pt: GNN encoder weights
• —edge_clf_best.pt: edge relation classifier weights
• —rel2id.json: mapping of relation string -> class id
• —config.json: metadata

How to use (concept)

1. 1.Build a graph Data(x, edgeindex, edgetype)
2. 2.Run encoder -> h
3. 3.Add AWGN to h (optional)
4. 4.Predict relations with edge_clf(h[src], h[dst])

Trained with AWGN augmentation (random SNR 0–20 dB).