* Add weight based edge sampler
* Can run, edge weight work.
TODO: test node weight
* Fix node weight sample
* Fix y
* Update doc
* Fix syntex
* Fix
* Fix GPU test for sampler
* Fix test
* Fix
* Refactor EdgeSampler to act as class object not function that it
can record its own private states.
* clean
* Fix
* Fix
* Fix run bug on kg app
* update
* update test
* test
* Simply python API and fix some C code
* Fix
* Fix
* Fix syntex
* Fix
* Update API description
* add replacement for edge sampler
* Now edge sampler support replacement and no-replacement
* Fix
* Fix
* change kg/app to use edge sampler with replacement config
* Update replacement algo
* Fix syntax
* Update
* Update
Co-authored-by: Da Zheng <zhengda1936@gmail.com>
* Add weight based edge sampler
* Can run, edge weight work.
TODO: test node weight
* Fix node weight sample
* Fix y
* Update doc
* Fix syntex
* Fix
* Fix GPU test for sampler
* Fix test
* Fix
* Refactor EdgeSampler to act as class object not function that it
can record its own private states.
* clean
* Fix
* Fix
* Fix run bug on kg app
* update
* update test
* test
* Simply python API and fix some C code
* Fix
* Fix
* Fix syntex
* Fix
* Update API description
* 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
* nonuniform sampler
* unit test
* test on out neighbors
* error checks
* lint
* fix
* clarification
* use macro switcher
* use empty array for uniform sampling
* oops
* Revert "oops"
This reverts commit a11f9ae707aaeb67fb5921c887a17d3711d5b04a.
* Revert "use empty array for uniform sampling"
This reverts commit 8526ce4cade89f2c1b09a08aca8830375ebafb31.
* re-reverting
* use a method
* rng refactor
* fix bugs
* unit test
* remove setsize
* lint
* fix test
* use explicit instantiation instead of inlining
* stricter test
* use tvm solution
* moved python interface to dgl.random
* lint
* address comments
* make getthreadid an inline function
* WIP: using object system for graph
* c++ side refactoring done; compiled
* remove stale apis
* fix bug in DGLGraphCreate; passed test_graph.py
* fix bug in python modify; passed utest for pytorch/cpu
* fix lint
* address comments
* random walk traces generation
* remove outdated comments
* oops put in the wrong place
* explicit inline
* moving rand_r to util
* pinsage-like model on movielens
* the code runs now
* support cuda
* using readonly graph
* moving random walk to public function
* per-thread seed and openmp support
* pinsage-like model on movielens
* the code runs now
* support cuda
* using readonly graph
* using C random walk
* removing profile decorators
* param initialization
* no grad
* leaky relu fixes everything
* train and save
* WIP
* WIP
* WIP
* seems to work
* evaluation output
* swapping order of val/test and train
* debug
* hyperparam tuning
* prior/training dataset split changes
* random walk reorg
* random walk with restart
* signed comparison fix
* migrating random walk to nodeflow
* Revert "migrating random walk to nodeflow"
This reverts commit f2565347cced7c912a58a529b257c033d9f375b7.
* add README and remove dataset
* new endpoint
* lint
* lint x2
* oops forgot test
* including bpr - better for baseline
* addressing fixes
* throwing random walks out from SamplerOp class
* forgot to move RandomWalk; why did this even work?
* removing legacy garbage
* add todo
* address comments
* stupid bug fix
* call ndarrayvector converter to handle traces
* random walk traces generation
* remove outdated comments
* oops put in the wrong place
* explicit inline
* moving rand_r to util
* moving random walk to public function
* per-thread seed and openmp support
* type cast styles
* remove loading backend in sse
* build mxnet in a second run
* a third run to fix everything
* fix docstring in sampler
* fix docstring in transformer
* README for doc build
* some reordering and printing
* use filename_pattern instead of ignore_pattern to reduce warning at the cost of redundant work...
* add env var to use mxnet in Jenkinsfile
* remove step 3, it's already fixed by previous commit
* add sse tutorial
* add mxnet tutorial ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* Fix ci
* Fix ci
* Fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* Fix CI
Fix CI image
* permission fix
* fix a bug in the code.
* small fix
* fix doc
* fix ci
* shorten the iters
* fix
* remove extra file
* add load_backend api to dynamically switch to another backend
* try fix
* fix tutorial
* fix tutorial
* fix bug in tutorial
Zihao Ye