Discrepancies in the Output of the k_hop_subgraph Function: Unexpected Additional Edges

[1234238]

🐛 Describe the bug

Specifically, I used the k_hop_subgraph function to find the one-hop neighbors of a target node. My target nodes are defined as torch.arange(gia_test.y.shape[0], gia_test.x.shape[0]), where gia_test.x represents the original dataset with some newly added nodes. Naturally, these new nodes introduce additional connections; however, I did not assign them any labels. My goal is to identify the original nodes to which these new nodes are connected.

To achieve this, I executed the following code. However, I was surprised to find that the resulting edge_index contained some extra nodes that I did not expect. I am unsure why this occurs—could this behavior be considered normal?

print(gia_test)
subset, gia_tar_edge_index, _, _ = k_hop_subgraph(torch.arange(gia_test.y.shape[0], gia_test.x.shape[0]), 1, gia_test.edge_index, relabel_nodes=False)

print(torch.arange(gia_test.y.shape[0], gia_test.x.shape[0]))
sorted_edges = torch.sort(gia_tar_edge_index, dim=0)[0]
directed_edge_index = torch.unique(sorted_edges, dim=1)

mask = directed_edge_index[1] < gia_test.y.shape[0]
print(directed_edge_index[:,mask])

Data(x=[2880, 302], edge_index=[2, 11496], y=[2680, 1], train_mask=[2680], val_mask=[2680], test_mask=[2680], target_idx=[804])
tensor([2680, 2681, 2682, 2683, 2684, 2685, 2686, 2687, 2688, 2689, 2690, 2691,
        2692, 2693, 2694, 2695, 2696, 2697, 2698, 2699, 2700, 2701, 2702, 2703,
        2704, 2705, 2706, 2707, 2708, 2709, 2710, 2711, 2712, 2713, 2714, 2715,
        2716, 2717, 2718, 2719, 2720, 2721, 2722, 2723, 2724, 2725, 2726, 2727,
        2728, 2729, 2730, 2731, 2732, 2733, 2734, 2735, 2736, 2737, 2738, 2739,
        2740, 2741, 2742, 2743, 2744, 2745, 2746, 2747, 2748, 2749, 2750, 2751,
        2752, 2753, 2754, 2755, 2756, 2757, 2758, 2759, 2760, 2761, 2762, 2763,
        2764, 2765, 2766, 2767, 2768, 2769, 2770, 2771, 2772, 2773, 2774, 2775,
        2776, 2777, 2778, 2779, 2780, 2781, 2782, 2783, 2784, 2785, 2786, 2787,
        2788, 2789, 2790, 2791, 2792, 2793, 2794, 2795, 2796, 2797, 2798, 2799,
        2800, 2801, 2802, 2803, 2804, 2805, 2806, 2807, 2808, 2809, 2810, 2811,
        2812, 2813, 2814, 2815, 2816, 2817, 2818, 2819, 2820, 2821, 2822, 2823,
        2824, 2825, 2826, 2827, 2828, 2829, 2830, 2831, 2832, 2833, 2834, 2835,
        2836, 2837, 2838, 2839, 2840, 2841, 2842, 2843, 2844, 2845, 2846, 2847,
        2848, 2849, 2850, 2851, 2852, 2853, 2854, 2855, 2856, 2857, 2858, 2859,
        2860, 2861, 2862, 2863, 2864, 2865, 2866, 2867, 2868, 2869, 2870, 2871,
        2872, 2873, 2874, 2875, 2876, 2877, 2878, 2879])
tensor([[  31,   64,   70,  258,  379,  409,  461,  569,  614,  719,  778,  915,
          936,  964,  971, 1015, 1044, 1145, 1274, 1349, 1408, 1448, 1561, 1667,
         1671, 1671, 1693, 1805, 2608],
        [1582, 1203, 2164, 2511, 2543, 1174, 1045, 2407, 2420, 1031, 2380, 2048,
         2153, 2633, 1485, 2356, 2311, 1237, 2586, 1601, 2240, 2198, 2671, 2550,
         2462, 2489, 2559, 1934, 2609]])

Versions

Collecting environment information...
PyTorch version: 2.0.0+cu118
Is debug build: False
CUDA used to build PyTorch: 11.8
ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.3) 9.4.0
Clang version: Could not collect
CMake version: version 3.25.0
Libc version: glibc-2.31

Python version: 3.8.8 (default, Apr 13 2021, 19:58:26)  [GCC 7.3.0] (64-bit runtime)
Python platform: Linux-5.15.0-124-generic-x86_64-with-glibc2.10
Is CUDA available: True
CUDA runtime version: 11.3.58
CUDA_MODULE_LOADING set to: LAZY

Versions of relevant libraries:
[pip3] flake8==7.1.1
[pip3] numpy==1.24.4
[pip3] torch==2.0.0+cu118
[pip3] torch-cluster==1.6.3+pt20cu118
[pip3] torch-geometric==2.6.1
[pip3] torch-scatter==2.1.2+pt20cu118
[pip3] torch-sparse==0.6.18+pt20cu118
[pip3] torch-spline-conv==1.2.2+pt20cu118
[pip3] torchaudio==2.0.1+cu118
[pip3] torchvision==0.15.1+cu118
[pip3] triton==2.0.0
[conda] numpy                     1.24.4                   pypi_0    pypi
[conda] torch                     2.0.0+cu118              pypi_0    pypi
[conda] torch-cluster             1.6.3+pt20cu118          pypi_0    pypi
[conda] torch-geometric           2.6.1                    pypi_0    pypi
[conda] torch-scatter             2.1.2+pt20cu118          pypi_0    pypi
[conda] torch-sparse              0.6.18+pt20cu118          pypi_0    pypi
[conda] torch-spline-conv         1.2.2+pt20cu118          pypi_0    pypi
[conda] torchaudio                2.0.1+cu118              pypi_0    pypi
[conda] torchvision               0.15.1+cu118             pypi_0    pypi
[conda] triton                    2.0.0                    pypi_0    pypi