ARXIV:2603.02025 · GRAPH NEURAL NETWORKS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

arXiv

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance. Addressing this challenge requires understanding how GNNs translate topological patterns into logical rules.

METHOD

Full abstract

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures. Addressing this challenge requires understanding how GNNs translate topological patterns into logical rules. However, current works only uncover the hard logical rules over graph concepts, which cannot quantify the contribution of each concept to prediction. Moreover, they are post-hoc interpretable methods that generate explanations after model training and may not accurately reflect the true combinatorial reasoning of GNNs, since they approximate it with a surrogate. In this work, we develop a graph concept bottleneck layer that can be integrated into any GNN architectures to guide them to predict the selected discriminative global graph concepts. The predicted concept scores are further projected to class labels by a sparse linear layer. It enforces the combinatorial reasoning of GNNs' predictions to fit the soft logical rule over graph concepts and thus can quantify the contribution of each concept. To further improve the quality of the concept bottleneck, we treat concepts as "graph words" and graphs as "graph sentences", and leverage language models to learn graph concept embeddings. Extensive experiments on multiple datasets show that our method GCBMs achieve state-of-the-art performance both in classification and interpretability.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. To further improve the quality of the concept bottleneck, we treat concepts as "graph words" and graphs as "graph sentences", and leverage language models…

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainA method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2603.02025 · GRAPH NEURAL NETWORKS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

arXiv

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainA method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.02025

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback55 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance. Addressing this challenge requires understanding how GNNs translate topological patterns into logical rules.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures. Addressing this challenge requires understanding how GNNs translate topological patterns into logical rules.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. To further improve the quality of the concept bottleneck, we treat concepts as "graph words" and graphs as "graph sentences", and leverage language models to learn graph concept embeddings.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Graph Neural Networks

Competitors

not indexed

Competitive landscape

A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.

Segment

Graph Neural Networks

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.02025 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(55)

Graph Concept Bottleneck Models

2025Haotian Xu, Tsui-Wei Weng et al.

Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Molecular Graph Learning

2025Jiahua Rao, Hanjing Lin et al.

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks

2025Jiaxing Zhang, Xiaoou Liu et al.

Concept Bottleneck Large Language Models

2024Chung-En Sun, Tuomas P. Oikarinen et al.

Graph Classification via Reference Distribution Learning: Theory and Practice

2024Zixiao Wang, Jicong Fan

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance

2024Divyansh Srivastava, Ge Yan et al.

GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules

2024Burouj Armgaan, Manthan Dalmia et al.

Interpreting Pretrained Language Models via Concept Bottlenecks

2023Zhen Tan, Lu Cheng et al.

In Silico and In Vitro Search for Dual Inhibitors of the Trypanosoma brucei and Leishmania major Pteridine Reductase 1 and Dihydrofolate Reductase

2023K. Possart, F. Herrmann et al.

Interpretable Prototype-based Graph Information Bottleneck

2023Sangwoo Seo, Sungwon Kim et al.

Discovery of rigid biphenyl Plasmodium falciparum DHFR inhibitors using a fragment linking strategy.

2023M. Hoarau, Patpanat Sermmai et al.

Label-Free Concept Bottleneck Models

2023Tuomas P. Oikarinen, Subhro Das et al.

Topological Pooling on Graphs

2023Yuzhou Chen, Y. Gel

Interpretable-by-Design Text Classification with Iteratively Generated Concept Bottleneck

2023Josh Magnus Ludan, Qing Lyu et al.

Graph Alignment Kernels using Weisfeiler and Leman Hierarchies

2023Giannis Nikolentzos, M. Vazirgiannis

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

2022Yue Yang, Artemis Panagopoulou et al.

Global Explainability of GNNs via Logic Combination of Learned Concepts

2022Steve Azzolin, Antonio Longa et al.

Structural Entropy Guided Graph Hierarchical Pooling

2022Junran Wu, Xueyuan Chen et al.

Task-Agnostic Graph Explanations

2022Yaochen Xie, S. Katariya et al.

Structure-Aware Transformer for Graph Representation Learning

2022Dexiong Chen, Leslie O’Bray et al.

Showing 20 of 55 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

none indexed

Extension

Builds On ThisBeyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

0.0

Commercially relevant

Higher ViabilityLearning Concept Bottleneck Models from Mechanistic Explanations

7.0

Higher ViabilityBeyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

7.0

Higher ViabilityRethinking Concept Bottleneck Models: From Pitfalls to Solutions

7.0

Higher ViabilitySCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning

7.0

Conflicting

Competing ApproachSCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing

2.0

Competing ApproachMLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

4.0

Competing ApproachCGRL: Causal-Guided Representation Learning for Graph Out-of-Distribution Generalization

4.0

Competing ApproachCausal Neighbourhood Learning for Invariant Graph Representations

4.0

Competing ApproachUnifying approach to uniform expressivity of graph neural networks

2.0

Related Resources

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.02025
Route: /paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer
Active tab: read
Artifact: revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer/paper-pack
REST build passport API/api/v1/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "a70d5294-d073-4370-bbce-582e5c46a27d",
  "arxiv_id": "2603.02025",
  "canonical_route": "/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
  "endpoints": {
    "paper_pack": "/api/v1/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer/paper-pack",
    "build_passport": "/api/v1/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

Canonical ID revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer | Route /paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.02025"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer",
  "normalized_query": "2603.02025",
  "route": "/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
  "paper_ref": "revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

/buildability/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

Watchwatch

Subject: Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

Paper ref

revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer

arXiv id

2603.02025

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

4fb47ef4a5fc684b86e4c35f03f9e6224a2527042afc2237fa06c8914f980531

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer#webpage",
      "url": "https://sciencetostartup.com/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
      "name": "Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer",
      "description": "A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer#scholarlyArticle",
      "headline": "Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer",
      "description": "A method for integrating graph concept bottleneck layers in GNNs to enhance interpretability and performance.",
      "url": "https://sciencetostartup.com/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer",
      "sameAs": "https://arxiv.org/abs/2603.02025",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.02025"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-02T16:07:24.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "466eb9ae3c2512470761b93738c917a7c810a862"
          },
          "url": "https://www.semanticscholar.org/paper/466eb9ae3c2512470761b93738c917a7c810a862"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c318e03e8fb000ed9baf6ef4675da43afd8804aa"
          },
          "url": "https://www.semanticscholar.org/paper/c318e03e8fb000ed9baf6ef4675da43afd8804aa"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "73dcdd4eb8ee812850bb676a310a89fdf1111dba"
          },
          "url": "https://www.semanticscholar.org/paper/73dcdd4eb8ee812850bb676a310a89fdf1111dba"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b0b131c9be1d9b2c54b06a5c0df1db55c296e15b"
          },
          "url": "https://www.semanticscholar.org/paper/b0b131c9be1d9b2c54b06a5c0df1db55c296e15b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7ee590d062df234ecf77e2c16d7280198aaafb09"
          },
          "url": "https://www.semanticscholar.org/paper/7ee590d062df234ecf77e2c16d7280198aaafb09"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0d8e3d42a2b9cd6e5d94ee4ecc3d1d50bc1ebb29"
          },
          "url": "https://www.semanticscholar.org/paper/0d8e3d42a2b9cd6e5d94ee4ecc3d1d50bc1ebb29"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "db1e76043592fb01c9f31feaea7555244e91cdb9"
          },
          "url": "https://www.semanticscholar.org/paper/db1e76043592fb01c9f31feaea7555244e91cdb9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4a97fe464d8e06d3af7ca9582f06eec816412a83"
          },
          "url": "https://www.semanticscholar.org/paper/4a97fe464d8e06d3af7ca9582f06eec816412a83"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cebd5b9f659d1f93d95524158e104e6b7c330bfc"
          },
          "url": "https://www.semanticscholar.org/paper/cebd5b9f659d1f93d95524158e104e6b7c330bfc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e5cd97345a843d90d6e0da00cd1ae689988feb62"
          },
          "url": "https://www.semanticscholar.org/paper/e5cd97345a843d90d6e0da00cd1ae689988feb62"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1d603b03bb083a2c3e2e3b6f116cf196d637e6b6"
          },
          "url": "https://www.semanticscholar.org/paper/1d603b03bb083a2c3e2e3b6f116cf196d637e6b6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "77d14bbaece056f5a94231f46f02cca86e9bc085"
          },
          "url": "https://www.semanticscholar.org/paper/77d14bbaece056f5a94231f46f02cca86e9bc085"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6d1badc223cfca6ae23fcce811b9dbcb8645cdef"
          },
          "url": "https://www.semanticscholar.org/paper/6d1badc223cfca6ae23fcce811b9dbcb8645cdef"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5bce30f98caa5decac63ef6cf58f5580b4c17883"
          },
          "url": "https://www.semanticscholar.org/paper/5bce30f98caa5decac63ef6cf58f5580b4c17883"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0940a66542957fbab6148d85e59a699343fd4db8"
          },
          "url": "https://www.semanticscholar.org/paper/0940a66542957fbab6148d85e59a699343fd4db8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e76317b5191b88d83758be322c026af77492de44"
          },
          "url": "https://www.semanticscholar.org/paper/e76317b5191b88d83758be322c026af77492de44"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ea0e4a9778e33b7f8e7b3246d63071330950995a"
          },
          "url": "https://www.semanticscholar.org/paper/ea0e4a9778e33b7f8e7b3246d63071330950995a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "afe13acf0a5a5c126d0394e09a5a55616d581128"
          },
          "url": "https://www.semanticscholar.org/paper/afe13acf0a5a5c126d0394e09a5a55616d581128"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7de413da6e0a00e14270cfaed2a31666e7c28747"
          },
          "url": "https://www.semanticscholar.org/paper/7de413da6e0a00e14270cfaed2a31666e7c28747"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0d4184cff17f093e0487b27180be515c385feff6"
          },
          "url": "https://www.semanticscholar.org/paper/0d4184cff17f093e0487b27180be515c385feff6"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Graph Neural Networks"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Graph Neural Networks",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Revealing Combinatorial Reasoning of GNNs via Graph Concept ",
          "item": "https://sciencetostartup.com/paper/revealing-combinatorial-reasoning-of-gnns-via-graph-concept-bottleneck-layer"
        }
      ]
    }
  ]
}

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(55)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(55)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline