# egordm/mgtcom architecture

> Architecture diagram of the GitHub repository egordm/mgtcom, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-01-19). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/egordm/mgtcom
- Repository: https://github.com/egordm/mgtcom

## Overview

##### Main Components

a) Core Framework Components:
- Data Processing Layer
- Model Variants Layer
- Embedding Generation Layer
- Community Detection Layer
- Evaluation Layer

b) Supporting Components:
- Dataset Management System
- Model Training Pipeline
- Baseline Models Integration
- Evaluation Metrics System

##### Detailed Architecture Breakdown

a) Data Layer:
- Data preprocessing pipeline (datasets/transforms/)
- Temporal and static data handling (datasets/temporal/ and datasets/static/)

b) Model Architecture:
- Create three parallel branches for model variants:
- MGTCOM (Combined temporal and topological)
- MGTCOM Topo (Topological only)
- MGTCOM Tempo (Temporal only)

c) Core Processing Pipeline:
- Data Sampling (ml/ml/data/samplers/)
- Feature Extraction (ml/ml/layers/)
- Embedding Generation (ml/ml/models/)
- Community Detection (ml/ml/algo/clustering/)
- Model Training (ml/ml/executors/)

##### Integration Points

- Connections between baseline models (GraphSAGE, Node2Vec, etc.)
- Evaluation pipeline (ml/ml/evaluation/)
- Callback system integration (ml/ml/callbacks/)

##### Specific Design Elements

Use the following visual elements:
- Blue rectangles: Core components
- Green rectangles: Data processing components
- Orange rectangles: Model variants
- Purple rectangles: Evaluation components

##### Important Details

- Data flow directions between components
- Temporal aspect handling
- Multimodal graph processing
- Community detection algorithms
- Integration points with baseline models
- Training and evaluation loops
- Configuration management (from ml/ml/utils/config.py)

##### Technical Specifications

- Python dependencies
- CUDA requirements
- Memory requirements
- Supported input formats
- Output formats

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph Input
        DS[("Input Datasets")]
        DS --> |DBLP| DSM["Dataset Management"]:::dsm
        DS --> |ICEWS| DSM
        DS --> |IMDB5000| DSM
    end

    subgraph "Data Processing"
        DSM --> DPL["Data Processing Layer"]:::dpl
        DPL --> SAM["Data Sampling"]:::sam
        DPL --> FP["Feature Processing"]:::fp
    end

    subgraph "Model Variants"
        SAM --> MGC["MGTCOM Combined"]:::mgc
        SAM --> MGT["MGTCOM Temporal"]:::mgt
        SAM --> MGP["MGTCOM Topological"]:::mgp
    end

    subgraph "Core Processing"
        MGC & MGT & MGP --> EMB["Embedding Generation"]:::emb
        EMB --> CD["Community Detection"]:::cd
    end

    subgraph "Training & Evaluation"
        CD --> TR["Training Pipeline"]:::tr
        TR --> EV["Evaluation System"]:::ev
        CB["Callback System"]:::cb --> TR
    end

    subgraph "Integration"
        BM["Baseline Models"]:::bm --> EMB
        CF["Model Configuration"]:::cf --> TR
    end

    subgraph "Output"
        EV --> MT["Evaluation Metrics"]:::mt
        MT --> RES["Results & Analysis"]
    end

    %% Component Mappings
    click DPL "https://github.com/egordm/MGTCOM/tree/master/datasets/datasets/transforms/"
    click DSM "https://github.com/egordm/MGTCOM/tree/master/datasets/datasets/temporal/"
    click MGC "https://github.com/egordm/MGTCOM/blob/master/ml/ml/models/mgcom_combi.py"
    click MGT "https://github.com/egordm/MGTCOM/blob/master/ml/ml/models/mgcom_tempo.py"
    click EMB "https://github.com/egordm/MGTCOM/blob/master/ml/ml/layers/embedding.py"
    click CD "https://github.com/egordm/MGTCOM/tree/master/ml/ml/algo/clustering/"
    click EV "https://github.com/egordm/MGTCOM/tree/master/ml/ml/evaluation/metrics/"
    click TR "https://github.com/egordm/MGTCOM/tree/master/ml/ml/executors/loops/"
    click BM "https://github.com/egordm/MGTCOM/tree/master/ml/ml/executors/baselines/"
    click SAM "https://github.com/egordm/MGTCOM/tree/master/ml/ml/data/samplers/"
    click CF "https://github.com/egordm/MGTCOM/blob/master/ml/ml/utils/config.py"
    click CB "https://github.com/egordm/MGTCOM/tree/master/ml/ml/callbacks/"
    click FP "https://github.com/egordm/MGTCOM/blob/master/ml/ml/layers/fc_net.py"
    click MT "https://github.com/egordm/MGTCOM/blob/master/ml/ml/evaluation/metrics/clustering.py"

    %% Styling
    classDef dpl fill:#90CAF9,stroke:#1976D2
    classDef dsm fill:#81C784,stroke:#388E3C
    classDef sam fill:#81C784,stroke:#388E3C
    classDef mgc fill:#FFB74D,stroke:#F57C00
    classDef mgt fill:#FFB74D,stroke:#F57C00
    classDef mgp fill:#FFB74D,stroke:#F57C00
    classDef emb fill:#90CAF9,stroke:#1976D2
    classDef cd fill:#90CAF9,stroke:#1976D2
    classDef tr fill:#CE93D8,stroke:#7B1FA2
    classDef ev fill:#CE93D8,stroke:#7B1FA2
    classDef bm fill:#FFB74D,stroke:#F57C00
    classDef cf fill:#90CAF9,stroke:#1976D2
    classDef cb fill:#90CAF9,stroke:#1976D2
    classDef fp fill:#81C784,stroke:#388E3C
    classDef mt fill:#CE93D8,stroke:#7B1FA2

    %% Legend
    subgraph Legend
        L1["Core Components"]:::dpl
        L2["Data Processing"]:::dsm
        L3["Model Variants"]:::mgc
        L4["Evaluation"]:::mt
    end
```
