Graph Explorer - Conftrace

Color:

Density

Advanced filters

Min weight: 2

Years: 2006 - 2026

Color = topic domain:

Machine Learning Deep Learning Computer Vision Natural Language Processing Reinforcement Learning Mathematics & Optimization Artificial Intelligence Robotics Speech & Audio Data Science & Analytics Healthcare & Medicine Computer Science Knowledge & Reasoning Interdisciplinary

Click a keyword to expand its co-occurrence neighborhood. Double-click to view papers.
Size = paper count. Line thickness = co-occurrence strength.

Louvain-detected research clusters from keyword co-occurrence.

Community:

What is a community? A group of keywords that co-occur on the same papers much more often than expected by chance (Louvain algorithm).
How to read: Node size = paper count. Color = dominant taxonomy domain. Lines = co-occurrence within the community.
Insight: Communities reveal how research subfields naturally cluster - they often cross taxonomy boundaries (e.g. NLP + ML keywords in the same community).

Depth:

How to read: Root keyword at top, specializations below. Size = paper count. Abbreviations shown in badges.
Example: "neural network" → children: "graph neural network" (GNN), "recurrent neural network" (RNN), etc.
Insight: Shows how broad concepts break into niche sub-areas. Click a leaf to expand further.

Try:

Showing top-level topic domains and their connections via shared papers.

Each bubble = a research domain (14 total). Size = number of papers.
Lines connect domains that share papers classified in both areas. Thicker = more shared.

Keywords that connect the most topic domains -- research "bridges".

Show top:

"Bridge" keywords appear in papers spanning many research domains.
Greener = connects more domains. These are the most interdisciplinary methods.

Year: 2020

Keywords:

Slide through years to see how research focus shifted.
Each bar = a keyword from the selected year. Bar length = papers published that year. Press Play for a smooth race with counter updates every 0.1s.

Preview Feel

Controls only the right-hand live graph preview during playback.

Advanced physics

Burst 420 ms

Repulsion 18

Spring 82

Damping 0.85

Conference:

"DNA" = what makes this conference unique. Keywords scored by TF-IDF specificity.
Green = highly characteristic of this conference. Slate = common across all conferences.

Try:

Green endpoints + link = strong path
Keywords appear together on 2+ papers

Dashed amber = indirect link
Connected through a shared paper