search

VITA-Group / Graph-Mixture-of-Experts

[NeurIPS'23] Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling. Haotao Wang, Ziyu Jiang, Yuning You, Yan Han, Gaowen Liu, Jayanth Srinivasa, Ramana Rao Kompella, Zhangyang Wang
MIT License
30 stars 2 forks source link

Code Problems #4

Closed sutongxu closed 5 months ago

sutongxu commented 5 months ago

python main_pyg.py --dataset ogbg-molhiv -n 8 --n1 4 -k 4 -d 150 --device 0 --gnn gcn-spmoe --coef 1

Run the command as above, result: raise Exception(“Now using drop node, which doesn't support mixed training/eval yet!”) Exception: Now using drop node, which doesn't support mixed training/eval yet!

The problem is at line 305: else: raise Exception("Now using drop node, which doesn't support mixed training/eval yet!") print('Training mixed...') train_mixed(model, device, train_loader, train_loader_2hop, optimizer, dataset.task_type) print('Evaluating mixed...') train_perf = eval_mixed(model, device, train_loader, train_loader_2hop, evaluator) valid_perf = eval_mixed(model, device, valid_loader, valid_loader_2hop, evaluator) test_perf = eval_mixed(model, device, test_loader, test_loader_2hop, evaluator)

spidercatfly commented 5 months ago

I encountered the same issue, have you solved it? Is it because it only supports either all one-hop or all two-hop experts?

lin-uice commented 1 month ago

I encountered the same issue, have you solved it?