Pith Number

pith:YPL7GVZF

pith:2021:YPL7GVZFXPHQW4NBPG5OEQ2K4W

not attested not anchored not stored refs resolved

How Attentive are Graph Attention Networks?

Eran Yahav, Shaked Brody, Uri Alon

Graph Attention Networks use static attention that cannot express simple graph problems, fixed by reordering to create dynamic GATv2.

arxiv:2105.14491 v3 · 2021-05-30 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YPL7GVZFXPHQW4NBPG5OEQ2K4W}

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

Because GATs use a static attention mechanism, there are simple graph problems that GAT cannot express: in a controlled problem, we show that static attention hinders GAT from even fitting the training data. ... GATv2: a dynamic graph attention variant that is strictly more expressive than GAT.

C2weakest assumption

That the controlled synthetic problem is representative of the limitations that matter in real benchmarks, and that reordering the attention operations fully converts static attention into dynamic attention without side effects on optimization or generalization.

C3one line summary

GAT uses static attention where neighbor rankings ignore the query node and thus cannot express some graph problems; GATv2 enables dynamic attention and outperforms GAT on 11 OGB and other benchmarks with equal parameters.

References

70 extracted · 70 resolved · 5 Pith anchors

[1] Learning to represent programs with graphs 2018

[2] On the bottleneck of graph neural networks and its practical implications 2021

[3] Diffusion-convolutional neural networks 1993

[4] Neural Machine Translation by Jointly Learning to Align and Translate 2014 · arXiv:1409.0473

[5] Interaction networks for learning about objects, relations and physics 2016

Formal links

2 machine-checked theorem links

Cited by

28 papers in Pith

Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework

Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery

Learning Dynamic Stability Landscapes in Synchronization Networks

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey

DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning

Receipt and verification

First computed	2026-05-17T23:38:15.389458Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c3d7f35725bbcf0b71a179bae2434ae587aff5aaf0474de3a8ef794bf0c15a25

Aliases

arxiv: 2105.14491 · arxiv_version: 2105.14491v3 · doi: 10.48550/arxiv.2105.14491 · pith_short_12: YPL7GVZFXPHQ · pith_short_16: YPL7GVZFXPHQW4NB · pith_short_8: YPL7GVZF

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/YPL7GVZFXPHQW4NBPG5OEQ2K4W \
  | 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: c3d7f35725bbcf0b71a179bae2434ae587aff5aaf0474de3a8ef794bf0c15a25

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "044bcd14d1a2616432d49ef12852583c4df320ff08cd76da89b98519a36718e6",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2021-05-30T10:17:58Z",
    "title_canon_sha256": "215510f58299ba0a78cba7aa74025151976b6ef2c24a42b5114174673e589208"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2105.14491",
    "kind": "arxiv",
    "version": 3
  }
}