Papers › NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

19 Jun 2023NeurIPS 2023 11arXiv:2306.10792archive 2025-07-28

Yun Yi, Haokui Zhang, Rong Xiao, Nannan Wang, Xiaoyu Wang

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yuny220/NAR-Former-V2 officialmentioned in paperpytorchMITSyntology: 15 samples, 9 ran (0 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
6unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yuny220/NAR-Former-V2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

yuny220/NAR-Former-V2 official repository 15 samples, 9 ran (0 instrument-failed) · 6 unverified
flops_conv predictor/feature/onnx_flops.py ran MIT (permissive) · 744e1f1434f9addf · report fixture: signature node:MockNode/0/?, attrs:dict/0/?, maps:dict/0/? · returned tuple · level recorded 2026-09-26
flops_gemm predictor/feature/onnx_flops.py ran MIT (permissive) · 3b564242dd4a13a1 · report fixture: signature node:MockNode/0/?, attrs:dict/0/?, maps:dict/0/? · returned tuple · level recorded 2026-09-26
flops_matmal predictor/feature/onnx_flops.py ran MIT (permissive) · 0f7addd0143bea1b · report fixture: signature node:MockNode/0/?, attrs:dict/0/?, maps:dict/0/? · returned tuple · level recorded 2026-09-26
gen_Khop_adj predictor/model.py ran MIT (permissive) · 0bc8a6e84b43d28b · report fixture: signature edge_index:Tensor/2/int, n_tokens:int/0/int, k:int/0/int · returned Tensor · level recorded 2026-09-26
padding_for_batch predictor/data_process/data_and_encoding_generate.py ran MIT (permissive) · 16c95ce071090988 · report fixture: signature code:ndarray/2/float, adj:list/1/list · returned tuple · level recorded 2026-09-26
transform_operations predictor/data_process/gen_json_101.py ran MIT (permissive) · 9dbe158474b5367f · report fixture: signature ops:list/1/str · returned ndarray · level recorded 2026-09-26
transform_operations_category predictor/data_process/gen_json_101.py ran MIT (permissive) · 9ca1858f61f750f5 · report fixture: signature ops:list/1/str · returned list · level recorded 2026-09-26
transform_operations_category_101 predictor/data_process/data_and_encoding_generate.py ran MIT (permissive) · ed0dbb64178970b6 · report fixture: signature ops:list/1/str · returned list · level recorded 2026-09-26
transform_operations_category_201 predictor/data_process/data_and_encoding_generate.py ran MIT (permissive) · bf2419d10c0e8b96 · report fixture: signature ops:list/1/str · returned list · level recorded 2026-09-26
embed_attrs predictor/feature/node_feature.py unverified MIT (permissive) · 1e37af5cf5320cea · report
embed_op_code predictor/feature/node_feature.py unverified MIT (permissive) · ff46a1625a9d0cd1 · report
embed_shape predictor/feature/node_feature.py unverified MIT (permissive) · 40bf84d585a0d8fb · report
extract_graph_feature predictor/feature/graph_feature.py unverified MIT (permissive) · bde901526881c504 · report
extract_graph_feature_from_networkx predictor/feature/graph_feature.py unverified MIT (permissive) · cc00ffba3a90caea · report
parse_from_onnx predictor/feature/graph_feature.py unverified MIT (permissive) · c116bb9f8d8527b3 · report

Tasks

Graph Neural NetworkRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGraph Neural NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections