{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/label-free-node-classification-on-graphs-with","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","arxiv_id":"2310.04668","date":"2023-10-07","proceeding":null,"authors":["Zhikai Chen","Haitao Mao","Hongzhi Wen","Haoyu Han","Wei Jin","Haiyang Zhang","Hui Liu","Jiliang Tang"],"abstract":"In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to ensure promising performance. In contrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiency on text-attributed graphs. Yet, they face challenges in efficiently processing structural data and suffer from high inference costs. In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMs while mitigating their limitations. Specifically, LLMs are leveraged to annotate a small portion of nodes and then GNNs are trained on LLMs' annotations to make predictions for the remaining large portion of nodes. The implementation of LLM-GNN faces a unique challenge: how can we actively select nodes for LLMs to annotate and consequently enhance the GNN training? How can we leverage LLMs to obtain annotations of high quality, representativeness, and diversity, thereby enhancing GNN performance with less cost? To tackle this challenge, we develop an annotation quality heuristic and leverage the confidence scores derived from LLMs to advanced node selection. Comprehensive experimental results validate the effectiveness of LLM-GNN. In particular, LLM-GNN can achieve an accuracy of 74.9% on a vast-scale dataset \\products with a cost less than 1 dollar.","url_abs":"https://arxiv.org/abs/2310.04668v3","url_pdf":"https://arxiv.org/pdf/2310.04668v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"label-free-node-classification-on-graphs-with","repo_url":"https://github.com/currytang/llmgnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04668"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/CurryTang/LLMGNN","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/pmernyei/wiki-cs-dataset","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/currytang/llmgnn","reach":{"status":"ok"}}],"summary":{"ran":18,"ran_honours":1,"ran_draft_wrong":3,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":5,"repositories":1},"found_in_text":{"samples":19,"ran":17,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"6061fb3161a49f36","entry":"calc_ratios","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/calc_sim_neighbours.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/calc_sim_neighbours.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6061fb3161a49f36"}},{"code_sha256_prefix":"ddc2ead4604bc732","entry":"calculate_avg_cosine_similarities","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/analyze_datasets.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/analyze_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddc2ead4604bc732"}},{"code_sha256_prefix":"0b02ef4443cf1e77","entry":"calculate_connectivity_stats","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/analyze_datasets.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/analyze_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b02ef4443cf1e77"}},{"code_sha256_prefix":"f87b1e7f91458a7b","entry":"calculate_milestone_tree","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/inspect_milestone_tree.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/inspect_milestone_tree.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f87b1e7f91458a7b"}},{"code_sha256_prefix":"0778263c5d981ef7","entry":"get_all_descendants","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/inspect_milestone_tree.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/inspect_milestone_tree.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0778263c5d981ef7"}},{"code_sha256_prefix":"393a0d8988f753de","entry":"get_different_num","repo":"CurryTang/LLMGNN","repo_kind":"official","path":"src/helper/data.py","file_url":"https://github.com/CurryTang/LLMGNN/blob/HEAD/src/helper/data.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"393a0d8988f753de"}},{"code_sha256_prefix":"2b9ee849ce40d859","entry":"get_values","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/mysqldump_to_csv.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/mysqldump_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b9ee849ce40d859"}},{"code_sha256_prefix":"7841874972fcbc73","entry":"inject_random_noise","repo":"CurryTang/LLMGNN","repo_kind":"official","path":"src/helper/data.py","file_url":"https://github.com/CurryTang/LLMGNN/blob/HEAD/src/helper/data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7841874972fcbc73"}},{"code_sha256_prefix":"0354e7c71fe7c820","entry":"is_insert","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/mysqldump_to_csv.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/mysqldump_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0354e7c71fe7c820"}},{"code_sha256_prefix":"e2a07418f83e3b77","entry":"keep_first_n_words","repo":"CurryTang/LLMGNN","repo_kind":"official","path":"src/llm.py","file_url":"https://github.com/CurryTang/LLMGNN/blob/HEAD/src/llm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2a07418f83e3b77"}},{"code_sha256_prefix":"a559c37cf21d8253","entry":"label_set","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/process_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/process_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a559c37cf21d8253"}},{"code_sha256_prefix":"465405a2bbb6bd57","entry":"load_data","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"experiments/linkprediction/load_wiki.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/experiments/linkprediction/load_wiki.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"465405a2bbb6bd57"}},{"code_sha256_prefix":"7baee91fefde7b99","entry":"load_glove_dict","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/process_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/process_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7baee91fefde7b99"}},{"code_sha256_prefix":"04fc08ae6a6e7056","entry":"load_redirects","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/extract_full_data_for_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/extract_full_data_for_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04fc08ae6a6e7056"}},{"code_sha256_prefix":"d3648e98b2f4d8ef","entry":"load_wiki","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/calc_shortest_paths.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/calc_shortest_paths.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3648e98b2f4d8ef"}},{"code_sha256_prefix":"2003a5c4bbb37699","entry":"load_wiki","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/calc_sim_neighbours.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/calc_sim_neighbours.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2003a5c4bbb37699"}},{"code_sha256_prefix":"78364baf10dfdc68","entry":"most_common_number","repo":"CurryTang/LLMGNN","repo_kind":"official","path":"src/llm.py","file_url":"https://github.com/CurryTang/LLMGNN/blob/HEAD/src/llm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78364baf10dfdc68"}},{"code_sha256_prefix":"17e9b89c587f323d","entry":"page_titles_to_ids","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/extract_full_data_for_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/extract_full_data_for_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17e9b89c587f323d"}},{"code_sha256_prefix":"46b893445845c5f7","entry":"page_titles_to_labels","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/extract_full_data_for_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/extract_full_data_for_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46b893445845c5f7"}},{"code_sha256_prefix":"0199f42427faddb5","entry":"raw_data_dict","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/process_dataset.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/process_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0199f42427faddb5"}},{"code_sha256_prefix":"ca3bd8e13278c0f7","entry":"replace_args_with_dict_values","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/args.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/args.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca3bd8e13278c0f7"}},{"code_sha256_prefix":"50aabaf962cff885","entry":"values_sanity_check","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/mysqldump_to_csv.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/mysqldump_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50aabaf962cff885"}},{"code_sha256_prefix":"640e9a0511864dc6","entry":"bfs_component","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/calc_shortest_paths.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/calc_shortest_paths.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"640e9a0511864dc6"}},{"code_sha256_prefix":"71366d46fc7695ec","entry":"budget_density_query","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/active.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/active.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71366d46fc7695ec"}},{"code_sha256_prefix":"492a608a449a11f4","entry":"budget_density_query2","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/active.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/active.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"492a608a449a11f4"}},{"code_sha256_prefix":"a8799dcc333a0cdf","entry":"get_T_HOC","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/hoc.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/hoc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8799dcc333a0cdf"}},{"code_sha256_prefix":"d1b530f92e04557e","entry":"get_T_P_global","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/hoc.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/hoc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1b530f92e04557e"}},{"code_sha256_prefix":"26a4b05c4ea2e051","entry":"get_T_P_local","repo":"currytang/llmgnn","repo_kind":"official","path":"src/helper/hoc.py","file_url":"https://github.com/currytang/llmgnn/blob/HEAD/src/helper/hoc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26a4b05c4ea2e051"}},{"code_sha256_prefix":"7d905d3619fb5a98","entry":"get_category_sizes","repo":"pmernyei/wiki-cs-dataset","repo_kind":"found_in_text","path":"data_processing/pyscripts/inspect_milestone_tree.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/inspect_milestone_tree.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d905d3619fb5a98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}