Methods › Graphs › Graph Embeddings › Laplacian PE

Laplacian Positional Encodings

Laplacian PE

296 papers tagged archive 2025-07-28

Introduced by Vijay Prakash Dwivedi et al. in Benchmarking Graph Neural Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Laplacian eigenvectors represent a natural generalization of the Transformer positional encodings (PE) for graphs as the eigenvectors of a discrete line (NLP graph) are the cosine and sinusoidal functions. They help encode distance-aware information (i.e., nearby nodes have similar positional features and farther nodes have dissimilar positional features).

Hence, Laplacian Positional Encoding (PE) is a general method to encode node positions in a graph. For each node, its Laplacian PE is the k smallest non-trivial eigenvectors.

PaperSourceSee Code · graphdeeplearning/benchmarking-gnns

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Unfolded Laplacian Spectral Embedding (ULSE); Multi-dimensional Persistent Sheaf Laplacian (MPSL).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 296 · with a code link: 154 · where Syntology ran a sample: 53 (45 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (53 of 296 tagged: 45 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 296, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 275 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Representation Learning53
Graph Learning37
Node Classification37
Graph Representation Learning27
Graph Neural Network24
Prediction18
Graph Classification17
Graph Regression17
Link Prediction17
Contrastive Learning12
Drug Discovery12
Graph Attention12
Graph Generation12
Molecular Property Prediction12
Property Prediction12
Recommendation Systems11
Denoising10
Decoder9
Self-Supervised Learning9
Language Modelling8

Usage over time archive 2025-07-28

Papers per year tagged with Laplacian PE: 2020 to 2025, peak 99 99 0 2020: 3 papers 2020 2021: 26 papers 2021 2022: 44 papers 2022 2023: 85 papers 2023 2024: 99 papers 2024 2025: 39 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (296 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Graph Embeddings

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