{"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/multi-task-graph-autoencoders","title":"Multi-Task Graph Autoencoders","arxiv_id":"1811.02798","date":"2018-11-07","proceeding":null,"authors":["Phi Vu Tran"],"abstract":"We examine two fundamental tasks associated with graph representation\nlearning: link prediction and node classification. We present a new autoencoder\narchitecture capable of learning a joint representation of local graph\nstructure and available node features for the simultaneous multi-task learning\nof unsupervised link prediction and semi-supervised node classification. Our\nsimple, yet effective and versatile model is efficiently trained end-to-end in\na single stage, whereas previous related deep graph embedding methods require\nmultiple training steps that are difficult to optimize. We provide an empirical\nevaluation of our model on five benchmark relational, graph-structured datasets\nand demonstrate significant improvement over three strong baselines for graph\nrepresentation learning. Reference code and data are available at\nhttps://github.com/vuptran/graph-representation-learning","url_abs":"http://arxiv.org/abs/1811.02798v1","url_pdf":"http://arxiv.org/pdf/1811.02798v1.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":"multi-task-graph-autoencoders","repo_url":"https://github.com/vuptran/graph-representation-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-citeseer","task":"Link Prediction","dataset":"Citeseer","model":"MTGAE","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy":"94.90%"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-cora","task":"Link Prediction","dataset":"Cora","model":"MTGAE","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy":"94.60%"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-pubmed","task":"Link Prediction","dataset":"Pubmed","model":"MTGAE","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy":"94.40%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"MTGAE","rank_in_archive_order":47,"of":71,"metrics":{"Accuracy":"71.80%","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"MTGAE","rank_in_archive_order":67,"of":73,"metrics":{"Accuracy":"79.00%","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"MTGAE","rank_in_archive_order":32,"of":70,"metrics":{"Accuracy":"80.40%","Training Split":"20 per node","Validation":"YES"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.02798"}},"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/vuptran/graph-representation-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"c1d6392f89c5e495","entry":"parse_index_file","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils_gcn.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils_gcn.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1d6392f89c5e495"}},{"code_sha256_prefix":"b32fd748b4bbe3bf","entry":"sample_mask","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils_gcn.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils_gcn.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b32fd748b4bbe3bf"}},{"code_sha256_prefix":"2d128671555b038c","entry":"ce","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/models/ae.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/models/ae.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":"2d128671555b038c"}},{"code_sha256_prefix":"96f5675b12d0ae3d","entry":"load_citation_data","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils_gcn.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils_gcn.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":"96f5675b12d0ae3d"}},{"code_sha256_prefix":"31a254ca3067d459","entry":"load_mat_data","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils.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":"31a254ca3067d459"}},{"code_sha256_prefix":"febbe76a03b60d62","entry":"lr_poly_decay","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils.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":"febbe76a03b60d62"}},{"code_sha256_prefix":"da12f129fccef718","entry":"mbce","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/models/ae.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/models/ae.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":"da12f129fccef718"}},{"code_sha256_prefix":"0ca4e904762a05db","entry":"mvn","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/models/ae.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/models/ae.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":"0ca4e904762a05db"}},{"code_sha256_prefix":"b5a670bde4ab55d0","entry":"split_train_test","repo":"vuptran/graph-representation-learning","repo_kind":"official","path":"longae/utils.py","file_url":"https://github.com/vuptran/graph-representation-learning/blob/HEAD/longae/utils.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":"b5a670bde4ab55d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}