# raghava-2812/adaptive-full-triple-matcher architecture

> Architecture diagram of the GitHub repository raghava-2812/adaptive-full-triple-matcher, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/raghava-2812/adaptive-full-triple-matcher
- Repository: https://github.com/raghava-2812/adaptive-full-triple-matcher

## Overview

Full-Triple-Matcher is a research project for integrating heterogeneous knowledge graphs. Its documented workflow loads two graphs, calculates predicate functionality, generates entity and predicate candidates, compares triples, updates pair probabilities, thresholds matches, and evaluates results; triple matching can also run separately. The graph includes the sampled semantic-similarity layer and documented alignment/evaluation branches. Some README-described A-FTM modules are absent from the supplied tree, so they are not represented as source nodes; implementation details beyond the excerpts are uncertain.

Main entry points: [`codes/entity-matching/FTM - early stop.ipynb`](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb) (Match Thresholding), [`codes/triple-matching/Calculate triple similarity.ipynb`](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/triple-matching/Calculate%20triple%20similarity.ipynb) (Standalone Triple Matching), [`dataset`](https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/dataset) (KGs and Gold Data), [`codes/entity-matching/graph_similarity.py`](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/graph_similarity.py) (Value Similarity)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_inputs["KG Inputs"]
  node_kg_data[("KGs and Gold Data")]
end

subgraph group_matching["Matching"]
  node_load_graphs["Load KG Pair"]
  node_predicate_stats["Predicate Statistics"]
  node_candidate_generation["Candidate Generation"]
  node_triple_comparison["Full-Triple Comparison"]
  node_pair_update["Pair Probability Update"]
  node_decision["Match Thresholding"]
  node_entity_alignment["Entity Alignment"]
  node_schema_alignment["Schema Alignment"]
  node_triple_matching["Standalone Triple Matching"]
end

subgraph group_evaluation["Evaluation"]
  node_match_results["Match Results"]
  node_topk_results["Hit@K Results"]
  node_triple_results["Triple Similarities"]
end

subgraph group_similarity["Similarity Layer"]
  node_base_similarity["Value Similarity"]
  node_semantic_types["Semantic Type Evidence"]
end

node_researcher(("Researcher"))

node_researcher -->|"runs workflow"| node_load_graphs
node_kg_data -->|"supplies graphs"| node_load_graphs
node_load_graphs -->|"precedes statistics"| node_predicate_stats
node_predicate_stats -->|"precedes candidates"| node_candidate_generation
node_candidate_generation -->|"precedes comparison"| node_triple_comparison
node_triple_comparison -->|"updates probabilities"| node_pair_update
node_pair_update -->|"precedes threshold"| node_decision
node_decision -->|"evaluates matches"| node_match_results
node_decision -->|"evaluates ranking"| node_topk_results
node_researcher -.->|"runs optionally"| node_triple_matching
node_kg_data -.->|"provides triples"| node_triple_matching
node_triple_matching -->|"produces similarities"| node_triple_results
node_base_similarity -->|"uses type evidence"| node_semantic_types
node_base_similarity -.->|"scores values"| node_triple_comparison
node_decision -.->|"yields entity pairs"| node_entity_alignment
node_researcher -.->|"uses alignment tools"| node_schema_alignment

click node_kg_data "https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/dataset"
click node_load_graphs "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb"
click node_predicate_stats "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20Calculate%20inverse%20functionality.ipynb"
click node_candidate_generation "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb"
click node_triple_comparison "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb"
click node_pair_update "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb"
click node_decision "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb"
click node_entity_alignment "https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/codes/entity-matching"
click node_schema_alignment "https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/codes/entity-matching"
click node_triple_matching "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/triple-matching/Calculate%20triple%20similarity.ipynb"
click node_match_results "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/Analyze%20paris%20and%20ftm%20matches.ipynb"
click node_topk_results "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/Analyzing%20top%40n.ipynb"
click node_triple_results "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/triple-matching/Calculate%20triple%20similarity.ipynb"
click node_base_similarity "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/graph_similarity.py"
click node_semantic_types "https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/semantic_type_matcher.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_kg_data toneBlue
class node_load_graphs,node_predicate_stats,node_candidate_generation,node_triple_comparison,node_pair_update,node_decision,node_entity_alignment,node_schema_alignment,node_triple_matching toneAmber
class node_match_results,node_topk_results,node_triple_results toneMint
class node_base_similarity,node_semantic_types toneRose
class node_researcher toneIndigo
```

## Components

### KG Inputs

- [KGs and Gold Data](https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/dataset): `dataset`

### Matching

- [Load KG Pair](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb): `codes/entity-matching/FTM - early stop.ipynb`
- [Predicate Statistics](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20Calculate%20inverse%20functionality.ipynb): `codes/entity-matching/FTM - Calculate inverse functionality.ipynb`
- [Candidate Generation](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb): `codes/entity-matching/FTM - early stop.ipynb`
- [Full-Triple Comparison](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb): `codes/entity-matching/FTM - early stop.ipynb`
- [Pair Probability Update](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb): `codes/entity-matching/FTM - early stop.ipynb`
- [Match Thresholding](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/FTM%20-%20early%20stop.ipynb): `codes/entity-matching/FTM - early stop.ipynb`
- [Entity Alignment](https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/codes/entity-matching): `codes/entity-matching`
- [Schema Alignment](https://github.com/raghava-2812/adaptive-full-triple-matcher/tree/main/codes/entity-matching): `codes/entity-matching`
- [Standalone Triple Matching](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/triple-matching/Calculate%20triple%20similarity.ipynb): `codes/triple-matching/Calculate triple similarity.ipynb`

### Evaluation

- [Match Results](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/Analyze%20paris%20and%20ftm%20matches.ipynb): `codes/entity-matching/Analyze paris and ftm matches.ipynb`
- [Hit@K Results](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/Analyzing%20top%40n.ipynb): `codes/entity-matching/Analyzing top@n.ipynb`
- [Triple Similarities](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/triple-matching/Calculate%20triple%20similarity.ipynb): `codes/triple-matching/Calculate triple similarity.ipynb`

### Similarity Layer

- [Value Similarity](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/graph_similarity.py): `codes/entity-matching/graph_similarity.py`
- [Semantic Type Evidence](https://github.com/raghava-2812/adaptive-full-triple-matcher/blob/main/codes/entity-matching/semantic_type_matcher.py): `codes/entity-matching/semantic_type_matcher.py`

### Other components

- **Researcher**

## Connections

- Researcher → Load KG Pair: runs workflow (evidence: `README.md`)
- KGs and Gold Data → Load KG Pair: supplies graphs (evidence: `README.md`)
- Load KG Pair → Predicate Statistics: precedes statistics (evidence: `README.md`)
- Predicate Statistics → Candidate Generation: precedes candidates (evidence: `README.md`)
- Candidate Generation → Full-Triple Comparison: precedes comparison (evidence: `README.md`)
- Full-Triple Comparison → Pair Probability Update: updates probabilities (evidence: `README.md`)
- Pair Probability Update → Match Thresholding: precedes threshold (evidence: `README.md`)
- Match Thresholding → Match Results: evaluates matches (evidence: `README.md`)
- Match Thresholding → Hit@K Results: evaluates ranking (evidence: `README.md`)
- Researcher → Standalone Triple Matching: runs optionally (evidence: `README.md`)
- KGs and Gold Data → Standalone Triple Matching: provides triples (evidence: `README.md`)
- Standalone Triple Matching → Triple Similarities: produces similarities (evidence: `README.md`)
- Value Similarity → Semantic Type Evidence: uses type evidence (evidence: `codes/entity-matching/graph_similarity.py`)
- Value Similarity → Full-Triple Comparison: scores values
- Match Thresholding → Entity Alignment: yields entity pairs (evidence: `README.md`)
- Researcher → Schema Alignment: uses alignment tools (evidence: `README.md`)
