{"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/nar-former-v2-rethinking-transformer-for-1","title":"NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning","arxiv_id":"2306.10792","date":"2023-06-19","proceeding":"NeurIPS 2023 11","authors":["Yun Yi","Haokui Zhang","Rong Xiao","Nannan Wang","Xiaoyu Wang"],"abstract":"As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target attributes of networks without the need for actual training and deployment procedures, facilitating efficient network deployment and design. Recently, inspired by the success of Transformer, some Transformer-based representation learning frameworks have been proposed and achieved promising performance in handling cell-structured models. However, graph neural network (GNN) based approaches still dominate the field of learning representation for the entire network. In this paper, we revisit Transformer and compare it with GNN to analyse their different architecture characteristics. We then propose a modified Transformer-based universal neural network representation learning model NAR-Former V2. It can learn efficient representations from both cell-structured networks and entire networks. Specifically, we first take the network as a graph and design a straightforward tokenizer to encode the network into a sequence. Then, we incorporate the inductive representation learning capability of GNN into Transformer, enabling Transformer to generalize better when encountering unseen architecture. Additionally, we introduce a series of simple yet effective modifications to enhance the ability of the Transformer in learning representation from graph structures. Our proposed method surpasses the GNN-based method NNLP by a significant margin in latency estimation on the NNLQP dataset. Furthermore, regarding accuracy prediction on the NASBench101 and NASBench201 datasets, our method achieves highly comparable performance to other state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2306.10792v2","url_pdf":"https://arxiv.org/pdf/2306.10792v2.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":"nar-former-v2-rethinking-transformer-for-1","repo_url":"https://github.com/yuny220/NAR-Former-V2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.10792","atlas_url":"https://app.syntology.ai/?focus=2306.10792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10792"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/yuny220/NAR-Former-V2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"ran":0,"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":"1e37af5cf5320cea","entry":"embed_attrs","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/node_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/node_feature.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":"1e37af5cf5320cea"}},{"code_sha256_prefix":"ff46a1625a9d0cd1","entry":"embed_op_code","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/node_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/node_feature.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":"ff46a1625a9d0cd1"}},{"code_sha256_prefix":"40bf84d585a0d8fb","entry":"embed_shape","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/node_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/node_feature.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":"40bf84d585a0d8fb"}},{"code_sha256_prefix":"bde901526881c504","entry":"extract_graph_feature","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/graph_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/graph_feature.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":"bde901526881c504"}},{"code_sha256_prefix":"cc00ffba3a90caea","entry":"extract_graph_feature_from_networkx","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/graph_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/graph_feature.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":"cc00ffba3a90caea"}},{"code_sha256_prefix":"744e1f1434f9addf","entry":"flops_conv","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/onnx_flops.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/onnx_flops.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":"744e1f1434f9addf"}},{"code_sha256_prefix":"3b564242dd4a13a1","entry":"flops_gemm","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/onnx_flops.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/onnx_flops.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":"3b564242dd4a13a1"}},{"code_sha256_prefix":"0f7addd0143bea1b","entry":"flops_matmal","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/onnx_flops.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/onnx_flops.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":"0f7addd0143bea1b"}},{"code_sha256_prefix":"0bc8a6e84b43d28b","entry":"gen_Khop_adj","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/model.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/model.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":"0bc8a6e84b43d28b"}},{"code_sha256_prefix":"16c95ce071090988","entry":"padding_for_batch","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/data_process/data_and_encoding_generate.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/data_process/data_and_encoding_generate.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":"16c95ce071090988"}},{"code_sha256_prefix":"c116bb9f8d8527b3","entry":"parse_from_onnx","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/feature/graph_feature.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/feature/graph_feature.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":"c116bb9f8d8527b3"}},{"code_sha256_prefix":"9dbe158474b5367f","entry":"transform_operations","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/data_process/gen_json_101.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/data_process/gen_json_101.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":"9dbe158474b5367f"}},{"code_sha256_prefix":"9ca1858f61f750f5","entry":"transform_operations_category","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/data_process/gen_json_101.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/data_process/gen_json_101.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":"9ca1858f61f750f5"}},{"code_sha256_prefix":"ed0dbb64178970b6","entry":"transform_operations_category_101","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/data_process/data_and_encoding_generate.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/data_process/data_and_encoding_generate.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":"ed0dbb64178970b6"}},{"code_sha256_prefix":"bf2419d10c0e8b96","entry":"transform_operations_category_201","repo":"yuny220/NAR-Former-V2","repo_kind":"official","path":"predictor/data_process/data_and_encoding_generate.py","file_url":"https://github.com/yuny220/NAR-Former-V2/blob/HEAD/predictor/data_process/data_and_encoding_generate.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":"bf2419d10c0e8b96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}