[KG][Model] Knowledge graph embeddings (#888)

* upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* init version.

* change default value of regularization.

* avoid specifying adversarial_temperature

* use default eval_interval.

* remove original model.

* remove optimizer.

* set default value of num_proc

* set default value of log_interval.

* don't need to set neg_sample_size_valid.

* remove unused code.

* use uni_weight by default.

* unify model.

* rename model.

* remove unnecessary data sampler.

* remove the code for checkpoint.

* fix eval.

* raise exception in invalid arguments.

* remove RowAdagrad.

* remove unsupported score function for now.

* Fix bugs of kg
Update README

* Update Readme for mxnet distmult

* Update README.md

* Update README.md

* revert changes on dmlc

* add tests.

* update CI.

* add tests script.

* reorder tests in CI.

* measure performance.

* add results on wn18

* remove some code.

* rename the training script.

* new results on TransE.

* remove --train.

* add format.

* fix.

* use EdgeSubgraph.

* create PBGNegEdgeSubgraph to simplify the code.

* fix test

* fix CI.

* run nose for unit tests.

* remove unused code in dataset.

* change argument to save embeddings.

* test training and eval scripts in CI.

* check Pytorch version.

* fix a minor problem in config.

* fix a minor bug.

* fix readme.

* Update README.md

* Update README.md

* Update README.md

python/dgl/contrib/sampling/sampler.py

@@ -582,6 +582,9 @@ class EdgeSampler(object):
             assert g.number_of_edges() == len(relations)
         self._relations = relations
 
+        if batch_size < 0 or neg_sample_size < 0:
+            raise Exception('Invalid arguments')
+
         self._return_false_neg = return_false_neg
         self._batch_size = int(batch_size)
 

tests/scripts/task_kg_test.sh

+#!/bin/bash
+
+KG_DIR="./apps/kg/"
+
+function fail {
+    echo FAIL: $@
+    exit -1
+}
+
+function usage {
+    echo "Usage: $0 backend device"
+}
+
+# check arguments
+if [ $# -ne 2 ]; then
+    usage
+    fail "Error: must specify device and bakend"
+fi
+
+if [ "$2" == "cpu" ]; then
+    dev=-1
+elif [ "$2" == "gpu" ]; then
+    export CUDA_VISIBLE_DEVICES=0
+    dev=0
+else
+    usage
+    fail "Unknown device $2"
+fi
+
+export DGLBACKEND=$1
+export DGL_LIBRARY_PATH=${PWD}/build
+export PYTHONPATH=${PWD}/python:$KG_DIR:$PYTHONPATH
+export DGL_DOWNLOAD_DIR=${PWD}
+
+# test
+
+pushd $KG_DIR> /dev/null
+
+python3 -m nose -v --with-xunit tests/test_score.py || "run test_score.py on $1"
+
+if [ "$2" == "cpu" ]; then
+    # verify CPU training
+    python3 train.py --model DistMult --dataset FB15k --batch_size 128 \
+        --neg_sample_size 16 --hidden_dim 100 --gamma 500.0 --lr 0.1 --max_step 100 \
+        --batch_size_eval 16 --valid --test -adv --eval_interval 30 --eval_percent 0.01
+elif [ "$2" == "gpu" ]; then
+    # verify GPU training
+    python3 train.py --model DistMult --dataset FB15k --batch_size 128 \
+        --neg_sample_size 16 --hidden_dim 100 --gamma 500.0 --lr 0.1 --max_step 100 \
+        --batch_size_eval 16 --gpu 0 --valid --test -adv --eval_interval 30 --eval_percent 0.01
+
+    # verify mixed CPU GPU training
+    python3 train.py --model DistMult --dataset FB15k --batch_size 128 \
+        --neg_sample_size 16 --hidden_dim 100 --gamma 500.0 --lr 0.1 --max_step 100 \
+        --batch_size_eval 16 --gpu 0 --valid --test -adv --mix_cpu_gpu --eval_percent 0.01 \
+        --save_emb DistMult_FB15k_emb
+
+    # verify saving training result
+    python3 eval.py --model_name DistMult --dataset FB15k --hidden_dim 2000 \
+        --gamma 500.0 --batch_size 16 --gpu 0 --model_path DistMult_FB15k_emb/ --eval_percent 0.01
+fi
+
+popd > /dev/null