Creation of arxiv-2023 folder

datasets/arxiv-2023/README.md

@@ -0,0 +1,90 @@
+# ARXIV-2023
+
+## Dataset Description
+
+arxiv-2023 is collected to be compared with ogbn-arxiv. Both datasets represent directed citation networks where each node corresponds to a paper published on arXiv and each edge indicates one paper citing another.
+
+Statistics:
+- Nodes: 33868
+- Edges: 305672
+- Number of Classes: 40
+
+#### Citation
+
+- Original Source
+	+ [Website](https://github.com/TRAIS-Lab/LLM-Structured-Data)
+	+ LICENSE: [<license type>](<URL to license>)
+
+
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+- Current Version
+	+ [Website](https://github.com/TRAIS-Lab/LLM-Structured-Data)
+	+ LICENSE: [<license type>](<URL to license>)
+
+
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+- Previous Version
+	+ [Website](<URL to website>)
+	+ LICENSE: [<license type>](<URL to license>)
+
+
+## Available Tasks
+
+### <Task Name>
+
+
+
+- Task type: `NodeClassification`
+
+
+#### Citation
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+<!-- Insert the BibTeX citation into the above code block. -->
+
+## Preprocessing
+
+The data files and task config file in GLI format are transformed in arxiv-2023.ipynb file. Raw data aquried in TRAIS-Lab/LLM-Structured-Data folder.
+
+### Requirements
+
+```
+openai
+pytorch
+PyG
+ogb
+```
+
+

datasets/arxiv-2023/arxiv-2023.ipynb

@@ -16,14 +16,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "import torch\n",
     "import pandas as pd\n",
-    "import numpy"
+    "import numpy\n",
+    "import json"
    ]
   },
   {
@@ -110,10 +111,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 61,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "33868"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "num_nodes"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -122,7 +136,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -134,25 +148,32 @@
     "  feature=[\"Node/NodeFeature\"],\n",
     "  target=\"Node/NodeLabel\",\n",
     "  num_classes=40,\n",
-    "  train_set=train_mask,\n",
-    "  val_set=\n"
+    "  train_set=numpy.array(train_mask),\n",
+    "  val_set=numpy.array(val_mask),\n",
+    "  test_set=numpy.array(test_mask),\n",
+    "  task_id=\"1\"\n",
+    ")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 62,
    "metadata": {},
    "outputs": [
     {
-     "ename": "SyntaxError",
-     "evalue": "invalid syntax (3587969684.py, line 1)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;36m  Cell \u001b[0;32mIn[53], line 1\u001b[0;36m\u001b[0m\n\u001b[0;31m    hi=[y[i] for i <30000]\u001b[0m\n\u001b[0m                   ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
-     ]
+     "data": {
+      "text/plain": [
+       "torch.Size([2, 305672])"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
-   "source": []
+   "source": [
+    "edge_index.shape"
+   ]
   }
  ],
  "metadata": {

datasets/arxiv-2023/task_node_classification_1.json

@@ -7,15 +7,15 @@
     "target": "Node/NodeLabel",
     "num_classes": 40,
     "train_set": {
-        "file": "arxiv-2023__task_node_classification_1__96c4df545b7523dab7ea703813687c06.npz",
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
         "key": "train_set"
     },
     "val_set": {
-        "file": "arxiv-2023__task_node_classification_1__96c4df545b7523dab7ea703813687c06.npz",
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
         "key": "val_set"
     },
     "test_set": {
-        "file": "arxiv-2023__task_node_classification_1__96c4df545b7523dab7ea703813687c06.npz",
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
         "key": "test_set"
     }
 }