Edge Attention in GINConv

[erenpolat19]

🐛 Describe the bug

from torch_geometric.nn import GINEConv as BaseGINEConv, GINConv as BaseGINConv, LEConv as BaseLEConv

class GINConv(BaseGINConv):
    def forward(self, x: Union[Tensor, OptPairTensor], edge_index: Adj, edge_attr: OptTensor = None, edge_atten: OptTensor = None, size: Size = None) -> Tensor:
        """"""
        if isinstance(x, Tensor):
            x: OptPairTensor = (x, x)

        # propagate_type: (x: OptPairTensor)
        out = self.propagate(edge_index, x=x, edge_atten=edge_atten, size=size)

        x_r = x[1]
        if x_r is not None:
            out += (1 + self.eps) * x_r

        return self.nn(out)

    def message(self, x_j: Tensor, edge_atten: OptTensor = None) -> Tensor:
        if edge_atten is not None:
            return x_j * edge_atten
        else:
            return x_j

For reasons of CUDA/Nvidia driver compatibility, I have to use a newer version of torch geometric than the one that is written for this code (taken from the paper Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism (GSAT)). It seems like GINEConv and GINConv does not support edge_atten anymore and I get the error.

File "/home/eren/GSAT/src/models/conv_layers.py", line 21, in forward
out = self.propagate(edge_index, x=x, edge_atten=edge_atten, size=size)
TypeError: propagate() got an unexpected keyword argument 'edge_atten'

I haven't found anything in the documentation regarding using edge_attention/edge_weights for GIN/GINEConv layers. What can be a possible fix, can I find the old source files for GINConv and GINEConv anywhere?

Thank you,

Versions

PyTorch version: 2.4.1
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Rocky Linux 9.5 (Blue Onyx) (x86_64)
GCC version: (GCC) 11.5.0 20240719 (Red Hat 11.5.0-5)
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.34

Python version: 3.9.21 (main, Dec 11 2024, 16:24:11) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.14.0-503.19.1.el9_5.x86_64-x86_64-with-glibc2.34
Is CUDA available: False
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: Could not collect
Nvidia driver version: Could not collect
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 208
On-line CPU(s) list: 0-207
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) CPU Max 9470
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 52
Socket(s): 2
Stepping: 8
CPU(s) scaling MHz: 78%
CPU max MHz: 3500.0000
CPU min MHz: 800.0000
BogoMIPS: 4000.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 4.9 MiB (104 instances)
L1i cache: 3.3 MiB (104 instances)
L2 cache: 208 MiB (104 instances)
L3 cache: 210 MiB (2 instances)
NUMA node(s): 8
NUMA node0 CPU(s): 0-12,104-116
NUMA node1 CPU(s): 13-25,117-129
NUMA node2 CPU(s): 26-38,130-142
NUMA node3 CPU(s): 39-51,143-155
NUMA node4 CPU(s): 52-64,156-168
NUMA node5 CPU(s): 65-77,169-181
NUMA node6 CPU(s): 78-90,182-194
NUMA node7 CPU(s): 91-103,195-207
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected

Versions of relevant libraries:
[pip3] numpy==2.0.1
[pip3] performer-pytorch==1.1.4
[pip3] pytorch-lightning==2.5.0.post0
[pip3] torch==2.4.1
[pip3] torch_cluster==1.6.3+pt24cu124
[pip3] torch-geometric==2.6.1
[pip3] torch_scatter==2.1.2+pt24cu124
[pip3] torch_sparse==0.6.18+pt24cu124
[pip3] torch_spline_conv==1.2.2+pt24cu124
[pip3] torchaudio==2.4.1
[pip3] torchmetrics==1.6.1
[pip3] torchvision==0.19.1
[pip3] triton==3.0.0
[conda] blas 1.0 mkl
[conda] cuda-cudart 12.4.127 0 nvidia
[conda] cuda-cupti 12.4.127 0 nvidia
[conda] cuda-libraries 12.4.1 0 nvidia
[conda] cuda-nvrtc 12.4.127 0 nvidia
[conda] cuda-nvtx 12.4.127 0 nvidia
[conda] cuda-opencl 12.8.55 0 nvidia
[conda] cuda-runtime 12.4.1 0 nvidia
[conda] ffmpeg 4.3 hf484d3e_0 pytorch
[conda] libcublas 12.4.5.8 0 nvidia
[conda] libcufft 11.2.1.3 0 nvidia
[conda] libcurand 10.3.9.55 0 nvidia
[conda] libcusolver 11.6.1.9 0 nvidia
[conda] libcusparse 12.3.1.170 0 nvidia
[conda] libjpeg-turbo 2.0.0 h9bf148f_0 pytorch
[conda] libnvjitlink 12.4.127 0 nvidia
[conda] mkl 2023.1.0 h213fc3f_46344
[conda] mkl-service 2.4.0 py39h5eee18b_2
[conda] mkl_fft 1.3.11 py39h5eee18b_0
[conda] mkl_random 1.2.8 py39h1128e8f_0
[conda] numpy 2.0.1 py39h5f9d8c6_1
[conda] numpy-base 2.0.1 py39hb5e798b_1
[conda] performer-pytorch 1.1.4 pypi_0 pypi
[conda] pytorch 2.4.1 py3.9_cuda12.4_cudnn9.1.0_0 pytorch
[conda] pytorch-cuda 12.4 hc786d27_7 pytorch
[conda] pytorch-lightning 2.5.0.post0 pypi_0 pypi
[conda] pytorch-mutex 1.0 cuda pytorch
[conda] torch-cluster 1.6.3+pt24cu124 pypi_0 pypi
[conda] torch-geometric 2.6.1 pypi_0 pypi
[conda] torch-scatter 2.1.2+pt24cu124 pypi_0 pypi
[conda] torch-sparse 0.6.18+pt24cu124 pypi_0 pypi
[conda] torch-spline-conv 1.2.2+pt24cu124 pypi_0 pypi
[conda] torchaudio 2.4.1 py39_cu124 pytorch
[conda] torchmetrics 1.6.1 pypi_0 pypi
[conda] torchtriton 3.0.0 py39 pytorch
[conda] torchvision 0.19.1 py39_cu124 pytorch