PeterGriffinJin/Edgeformers
Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks (ICLR 2023)
This tool helps researchers and data scientists analyze complex relationships within networks where the connections themselves have descriptive text, like user reviews between products or comments between forum users. It takes structured data representing these textual connections and the entities they link, then outputs meaningful numerical representations (embeddings) for either the connections (edges) or the entities (nodes). This is ideal for those working on recommendation systems, content moderation, or social network analysis who need to understand nuanced relationships.
No commits in the last 6 months.
Use this if you need to extract numerical representations from networks where the 'links' between items or people are described by text, such as customer reviews or forum discussions.
Not ideal if your network data consists only of simple connections without any associated descriptive text on the edges, or if you are not comfortable with command-line operations.
Stars
71
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/PeterGriffinJin/Edgeformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
jtonglet/SEER
Code implementation for the EMNLP 2023 paper "SEER A Knapsack approach to Exemplar Selection for...
yzhan238/SemRank
The source code used for paper "Scientific Paper Retrieval with LLM-Guided Semantic-Based...
PeterGriffinJin/METAG
Learning Multiplex Representations on Text-Attributed Graphs with One Language Model Encoder