Graphormer model for Graph Classification (#20968)

* [FT] First commit for graphormer architecture.

The model has no tokenizer, as it uses a collator and preprocessing function for its input management.
Architecture to be tested against original one.
The arch might need to be changed to fit the checkpoint, but a revert to the original arch will make the code less nice to read.
TODO: doc

* [FIX] removed test model

* [FIX] import error

* [FIX] black and flake

* [DOC] added paper refs

* [FIX] [DOC]

* [FIX] black

* [DOC] Updated READMEs

* [FIX] Order of imports + rm Tokenizer calls

* [FIX] Moved assert in class to prevent doc build failure

* [FIX] make fix-copies

* [Doc] update from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* [FIX] Removed Graphormer from Sequence classification model list

* [DOC] Added HF copyright to Cython file

* [DOC] Fixed comments

* [FIX] typos in class doc + removed config classes.

Todo: update doc from paper definitions

* [FIX] Removed dependency to fairseq, and replaced all asserts with Exception management

* [FIX] Homogeneized initialization of weights to pretrained constructor

* [FIX] [CP] Updated multi_hop parameter to get same results as in original implementation

* [DOC] Relevant parameter description in the configuration file

* [DOC] Updated doc and comments in main graphormer file

* [FIX] make style and quality checks

* [DOC] Fix doc format

* [FIX] [WIP] Updated part of the tests, though still a wip

* [FIX] [WIP]

* [FIX] repo consistency

* [FIX] Changed input names for more understandability

* [FIX] [BUG] updated num_classes params for propagation in the model

* simplified collator

* [FIX] Updated tests to follow new naming pattern

* [TESTS] Updated test suite along with model

* |FIX] rm tokenizer import

* [DOC] add link to graphormerdoc

* Changed section in doc from text model to graph model

* Apply suggestions from code review

Spacing, inits
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* [DOC] Explain algos_graphormer functions

* Cython soft import protection

* Rm call to Callable in configuration graphormer

* [FIX] replaced asserts with Exceptions

* Add org to graphormer checkpoints

* Prefixed classes with Graphormer

* Management of init functions

* format

* fixes

* fix length file

* update indent

* relaunching ci

* Errors for missing cython imports

* fix style

* fix style doc
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

src/transformers/utils/__init__.py

@@ -103,6 +103,7 @@ from .import_utils import (
     is_bitsandbytes_available,
     is_bs4_available,
     is_coloredlogs_available,
+    is_cython_available,
     is_datasets_available,
     is_decord_available,
     is_detectron2_available,

src/transformers/utils/dummy_pt_objects.py

@@ -2865,6 +2865,30 @@ class GPTJPreTrainedModel(metaclass=DummyObject):
         requires_backends(self, ["torch"])
 
 
+GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST = None
+
+
+class GraphormerForGraphClassification(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
+class GraphormerModel(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
+class GraphormerPreTrainedModel(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
 GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST = None
 
 

src/transformers/utils/import_utils.py

@@ -736,6 +736,10 @@ def is_jumanpp_available():
     return (importlib.util.find_spec("rhoknp") is not None) and (shutil.which("jumanpp") is not None)
 
 
+def is_cython_available():
+    return importlib.util.find_spec("pyximport") is not None
+
+
 # docstyle-ignore
 DATASETS_IMPORT_ERROR = """
 {0} requires the 🤗 Datasets library but it was not found in your environment. You can install it with:

utils/check_repo.py

@@ -51,6 +51,8 @@ PRIVATE_MODELS = [
 # Being in this list is an exception and should **not** be the rule.
 IGNORE_NON_TESTED = PRIVATE_MODELS.copy() + [
     # models to ignore for not tested
+    "GraphormerEncoder",  # Building part of bigger (tested) model.
+    "GraphormerDecoderHead",  # Building part of bigger (tested) model.
     "CLIPSegDecoder",  # Building part of bigger (tested) model.
     "TableTransformerEncoder",  # Building part of bigger (tested) model.
     "TableTransformerDecoder",  # Building part of bigger (tested) model.
@@ -152,6 +154,8 @@ TEST_FILES_WITH_NO_COMMON_TESTS = [
 IGNORE_NON_AUTO_CONFIGURED = PRIVATE_MODELS.copy() + [
     # models to ignore for model xxx mapping
     "GitVisionModel",
+    "GraphormerModel",
+    "GraphormerForGraphClassification",
     "BlipForConditionalGeneration",
     "BlipForImageTextRetrieval",
     "BlipForQuestionAnswering",