README.md 655 Bytes
Newer Older
1
2
3
4
5
6
7
8
9
10
11
# Relational-GCN

### Prerequisites
Two extra python packages are needed for this example: 

- rdflib
- pandas

Example code was tested with rdflib 4.2.2 and pandas 0.23.4

### Entity Classification
12
AIFB: accuracy 97.22% (DGL), 95.83% (paper)
13
14
15
16
```
DGLBACKEND=mxnet python entity_classify.py -d aifb --testing --gpu 0
```

17
MUTAG: accuracy 76.47% (DGL), 73.23% (paper)
18
19
20
21
```
DGLBACKEND=mxnet python entity_classify.py -d mutag --l2norm 5e-4 --n-bases 40 --testing --gpu 0
```

22
BGS: accuracy 79.31% (DGL, n-basese=20, OOM when >20), 83.10% (paper)
23
24
25
```
DGLBACKEND=mxnet python entity_classify.py -d bgs --l2norm 5e-4 --n-bases 20 --testing --gpu 0 --relabel
```