Pith Number

pith:6YR3PRSJ

pith:2026:6YR3PRSJ4LIZ4AKOY62I4Q2RAJ

not attested not anchored not stored refs resolved

A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions

Abdoulaye Banir\'e Diallo, Mohamed Bouguessa, Mohamed Mahmoud Amar, Nairouz Mrabah

A unified contrastive framework learns graph representations by linearly combining node, proximity, cluster, and graph level signals with a parameter-free self-weighting mechanism.

arxiv:2605.12685 v1 · 2026-05-12 · cs.LG · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6YR3PRSJ4LIZ4AKOY62I4Q2RAJ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our approach not only enhances optimization flexibility but also eliminates the computational overhead of hyperparameter tuning in conventional multi-task GSSL methods. Comprehensive experiments on real-world datasets show that our methods consistently outperform state-of-the-art approaches across downstream tasks, including classification, clustering, and link prediction, in both single-level and multi-level scenarios.

C2weakest assumption

That a linear combination of per-level similarity and dissimilarity scores, modulated by the proposed self-weighting, captures complementary multi-level information without destructive interference or the need for level-specific tuning.

C3one line summary

A multi-level graph contrastive framework with adaptive self-weighting outperforms prior single-level and multi-task GSSL methods on classification, clustering, and link prediction.

References

63 extracted · 63 resolved · 1 Pith anchors

[1] Re- thinking deep clustering paradigms: Self-supervision is all you need, 2025

[2] Big self-supervised models are strong semi-supervised learners, 2020

[3] Toward convex manifolds: A geometric perspective for deep graph clus- tering of single-cell rna-seq data 2023

[4] Exploring the interaction between local and global latent configurations for clustering single-cell rna-seq: a unified per- spective, 2023

[5] Graph self-supervised learning: A survey, 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:49.937235Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f623b7c649e2d19e014ec7b48e43510272869b1d13df90b160b10406bc27ab8e

Aliases

arxiv: 2605.12685 · arxiv_version: 2605.12685v1 · doi: 10.48550/arxiv.2605.12685 · pith_short_12: 6YR3PRSJ4LIZ · pith_short_16: 6YR3PRSJ4LIZ4AKO · pith_short_8: 6YR3PRSJ

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/6YR3PRSJ4LIZ4AKOY62I4Q2RAJ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f623b7c649e2d19e014ec7b48e43510272869b1d13df90b160b10406bc27ab8e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5eed13d50b53827798cbd06df4036e31661bd9cbb5fd1143e13313a37e38587e",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T19:33:39Z",
    "title_canon_sha256": "3b4948d69bc0a6ca80d36b9d7e2ff5fd65a92e7c5842153cabc78d44b7040948"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12685",
    "kind": "arxiv",
    "version": 1
  }
}