{"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/llms-as-zero-shot-graph-learners-alignment-of","title":"LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings","arxiv_id":"2408.14512","date":"2024-08-25","proceeding":null,"authors":["Duo Wang","Yuan Zuo","FengZhi Li","Junjie Wu"],"abstract":"Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN's representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method's effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors.","url_abs":"https://arxiv.org/abs/2408.14512v3","url_pdf":"https://arxiv.org/pdf/2408.14512v3.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":"llms-as-zero-shot-graph-learners-alignment-of","repo_url":"https://github.com/w-rudder/tea-glm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"llms-as-zero-shot-graph-learners-alignment-of","repo_url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/token_learner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llms-as-zero-shot-graph-learners-alignment-of","repo_url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/token_learner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llms-as-zero-shot-graph-learners-alignment-of","repo_url":"https://github.com/MindSpore-scientific-2/code-2/tree/main/token_learner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2408.14512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14512"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/token_learner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-2/tree/main/token_learner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/token_learner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/w-rudder/tea-glm","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":8,"ran":0,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"2ede4c92b35f0844","entry":"get_title","repo":"w-rudder/tea-glm","repo_kind":"official","path":"GNNPreTrain/train_valid_paper.py","file_url":"https://github.com/w-rudder/tea-glm/blob/HEAD/GNNPreTrain/train_valid_paper.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ede4c92b35f0844"}},{"code_sha256_prefix":"665b410fa2e90913","entry":"create_dataset_info","repo":"MindSpore-scientific-2/code-2","repo_kind":"listed","path":"STCrowd/STCrowd_convert.py","file_url":"https://github.com/MindSpore-scientific-2/code-2/blob/HEAD/STCrowd/STCrowd_convert.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"665b410fa2e90913"}},{"code_sha256_prefix":"72814d7de33e5aef","entry":"decode","repo":"MindSpore-scientific-2/code-11","repo_kind":"listed","path":"AECRNet/data.py","file_url":"https://github.com/MindSpore-scientific-2/code-11/blob/HEAD/AECRNet/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72814d7de33e5aef"}},{"code_sha256_prefix":"16298c972234921e","entry":"generate_sample","repo":"MindSpore-scientific-2/code-11","repo_kind":"listed","path":"QuantExplainNLP_AlgoAnalysis/data_preprocessing.py","file_url":"https://github.com/MindSpore-scientific-2/code-11/blob/HEAD/QuantExplainNLP_AlgoAnalysis/data_preprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"16298c972234921e"}},{"code_sha256_prefix":"5919a74fc358ee01","entry":"get_feature_names","repo":"MindSpore-scientific-2/code-11","repo_kind":"listed","path":"QuantExplainNLP_AlgoAnalysis/explainability.py","file_url":"https://github.com/MindSpore-scientific-2/code-11/blob/HEAD/QuantExplainNLP_AlgoAnalysis/explainability.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5919a74fc358ee01"}},{"code_sha256_prefix":"6553960c96b0e666","entry":"load_group","repo":"MindSpore-scientific-2/code-2","repo_kind":"listed","path":"STCrowd/STCrowd_convert.py","file_url":"https://github.com/MindSpore-scientific-2/code-2/blob/HEAD/STCrowd/STCrowd_convert.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6553960c96b0e666"}},{"code_sha256_prefix":"ef93260b5137f73b","entry":"maybe_num_nodes","repo":"MindSpore-scientific-2/code-11","repo_kind":"listed","path":"RGNN/model_simple.py","file_url":"https://github.com/MindSpore-scientific-2/code-11/blob/HEAD/RGNN/model_simple.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ef93260b5137f73b"}},{"code_sha256_prefix":"da6a321dfe042d21","entry":"process_single_scene","repo":"MindSpore-scientific-2/code-2","repo_kind":"listed","path":"STCrowd/STCrowd_convert.py","file_url":"https://github.com/MindSpore-scientific-2/code-2/blob/HEAD/STCrowd/STCrowd_convert.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da6a321dfe042d21"}},{"code_sha256_prefix":"14c181fabe865cbf","entry":"set_random_seed","repo":"MindSpore-scientific-2/code-11","repo_kind":"listed","path":"AECRNet/data.py","file_url":"https://github.com/MindSpore-scientific-2/code-11/blob/HEAD/AECRNet/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14c181fabe865cbf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}