# Graph Data Science Library v1.5 now available!

**URL:** <https://community.neo4j.com/t/graph-data-science-library-v1-5-now-available/33491>\
**Category:** Graph Data Science / Graph Analytics\
**Created:** [February 9, 2021, 10:58pm UTC](https://community.neo4j.com/t/graph-data-science-library-v1-5-now-available/33491 "2021-02-09T22:58:50Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![alicia\_frame1](https://sea1.discourse-cdn.com/flex021/user_avatar/community.neo4j.com/alicia_frame1/32/6998_2.png) [@alicia\_frame1](https://community.neo4j.com/u/alicia_frame1)\
**Post date:** [February 9, 2021, 10:58pm UTC](https://community.neo4j.com/t/graph-data-science-library-v1-5-now-available/33491/1 "2021-02-09T22:58:50Z")

</div>

Graph Data Science Library v1.5 now available on[github](https://github.com/neo4j/graph-data-science/releases/tag/1.5.0), our [download center](https://neo4j.com/download-center/#algorithms), and desktop 🎉

This release includes:

- ML based link prediction and node classification (train a machine learning model in Neo4j; includes appropriate graph splitting and model selection to save only the best model) with `gds.alpha.ml.nodeClassification` and `gds.alpha.ml.linkPrediction`
  
- [Persistent](https://neo4j.com/docs/graph-data-science/1.5/model-catalog/model-catalog/#catalog-model-store)& [publishable](https://neo4j.com/docs/graph-data-science/1.5/model-catalog/model-catalog/#catalog-model-publish) models (train graphsage and persist your model through a db restart!) _(Enterprise only)_
  
- New algos: [speaker listener label propagation](https://neo4j.com/docs/graph-data-science/1.5/algorithms/sllpa/) & [HITS](https://neo4j.com/docs/graph-data-science/1.5/algorithms/hits/)
  
- New in memory graph compression format for Enterprise Edition users (up to 75% less memory!)
  
- [Export from the in-memory graph to CSV](https://neo4j.com/docs/graph-data-science/1.5/management-ops/graph-catalog-ops/#catalog-graph-export-csv)
  
- Pathfinding algos ([Dijkstra](https://neo4j.com/docs/graph-data-science/1.5/algorithms/dijkstra-source-target/), [Yen's](https://neo4j.com/docs/graph-data-science/1.5/algorithms/yens/), [A\*](https://neo4j.com/docs/graph-data-science/1.5/algorithms/astar/)) reimplemented and moved to the `beta` tier
  

Plus other bug fixes and improvements.  
  
Full details are available in the [release notes](https://neo4j.com/graph-data-science-1-5-0-release-notes/), and the docs are available at [https://neo4j.com/docs/graph-data-science/1.5/](https://neo4j.com/docs/graph-data-science/1.5/).

  

We've got a webinar scheduled for March 11th to walk through the new features and do a demo, sign up [here](https://neo4j.com/event/supervised-graph-machine-learning-now-in-neo4j/)

---

<div class="post-metadata">

**Author:** ![fabisch\_kamz](https://sea1.discourse-cdn.com/flex021/user_avatar/community.neo4j.com/fabisch_kamz/32/8388_2.png) [@fabisch\_kamz](https://community.neo4j.com/u/fabisch_kamz)\
**Post date:** [February 12, 2021, 9:58am UTC](https://community.neo4j.com/t/graph-data-science-library-v1-5-now-available/33491/2 "2021-02-12T09:58:29Z")

</div>

Already love this version of GDS