PhD student at National University of Singapore @NUSingapore | Graphs and LLMs | Google PhD Fellowship 2024
Joined October 2021
- Tweets45
- Following128
- Followers763
- Likes398
Graph learning at Google in 2026 @michael_galkin
๐Room 308, COEX
#ICML2026
Talk by Andy Huang @shenyangHuang on temporal graph foundation models
๐Room 308, COEX
#ICML2026 #GFM
GFM @ ICML 2026 is happening now!
๐ Room 308, COEX Seoul
Join us for invited talks, orals, posters, panel discussion, and awards on graph foundation models.
๐ sites.google.com/view/gfmicmโฆโฆ
#ICML2026 #GraphML #GFM
Xiaoxin He retweeted
Boosting Q&A Accuracy with GraphRAG powered by our G-Retriever architecture.
@he_xiaoxin
developer.nvidia.com/blog/boโฆ
Check out the paper here: arxiv.org/abs/2409.13265
I will be presenting G-Retriever tomorrow, Thu 12 Dec 4:30 p.m. PST โ 7:30 p.m. PST, at East Exhibit Hall A-C #4607.
neurips.cc/virtual/2024/postโฆ
๐ช๐๐๐ ๐๐๐๐ ๐๐๐๐ ๐ฎ๐๐๐๐ ๐ฃ๏ธ
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
ArXiv: arxiv.org/abs/2402.07630
GitHub: github.com/XiaoxinHe/G-Retriโฆ
BlogPost: medium.com/@xxhe/graph-retriโฆ
Xiaoxin He retweeted
I will give a talk at the @LogConference on "Integrating Graph Neural Networks and Large Language Models".
The conference is virtual, free to attend, live-streamed, and recorded.
logconference.org
Hope to see you there!
Thrilled to announce that I've been awarded the ๐๐ผ๐ผ๐ด๐น๐ฒ ๐ฃ๐ต๐ ๐๐ฒ๐น๐น๐ผ๐๐๐ต๐ถ๐ฝ! Huge thanks to my advisors, @BryanHooi1 and @xbresson, for their incredible support and guidance! Grateful to @GoogleAI for this valuable honor! ๐๐
research.google/programs-andโฆ
Awesome to see that PyG now supports G-Retriever!๐
arxiv.org/pdf/2402.07630
Excited to try out the new features in PyG 2.6!
๐ PyG 2.6 is here: GNNs + LLMs, PyTorch 2.4 and more! ๐
Weโre excited to announce the release of PyG 2.6.0, packed with incredible updates for graph learning!
Hereโs a quick rundown of whatโs new:
โจ Key Highlights:
-- GNNs + LLMs: New models like GRetriever that co-train LLaMA2 with GNNs for enhanced knowledge graph tasks.
-- PyTorch 2.4 Compatibility: Full support for PyTorch 2.4 across platforms!
-- Efficient Index Tensor Representation: Simplifying 1D indices with the new Index class for seamless interactions in GNN message passing.
-- Plus, there are new tutorials, multi-GPU examples, and various improvements to elevate your GNN workflows! ๐
Check out the full changelog and get started with PyG 2.6 today!
github.com/pyg-team/pytorch_โฆ
Xiaoxin He retweeted
We have seen great success in LoG 2023 local meetups in Stanford, NY, Munich, Amsterdam, Shanghai, Lausanne, Paris, Tromso, Madrid, Trento, Oxford, and Montreal. With over 700 attendees in total, the memories from LoG 2023 have been incredible!
Our new call for #LoG2024 local meetups is out! This "network" of local mini-conferences aims to bring together attendees belonging to the same geographic area, fostering discussions and collaborations.If you are interested in hosting one, please read this logconference.org/call-for-mโฆ
Xiaoxin He retweeted
Join the online LoGG presentation by @he_xiaoxin, hosted by @HannesStaerk @dom_beaini, on integrating LLMs and GNNs w/ G-Retriever.
When: Mon Jul 15 11am ET
Zoom: zoom.us/j/5775722530?pwd=Zzlโฆ
Blog: medium.com/@xxhe/graph-retriโฆ
ArXiv: arxiv.org/pdf/2402.07630.pdf
GitHub: github.com/XiaoxinHe/G-Retriโฆ
Xiaoxin He retweeted
Our new call for #LoG2024 local meetups is out! This "network" of local mini-conferences aims to bring together attendees belonging to the same geographic area, fostering discussions and collaborations.If you are interested in hosting one, please read this logconference.org/call-for-mโฆ
Xiaoxin He retweeted
Two exciting updates for the Learning on Graphs Conference!
1) Virtual conference from Nov 26th 2024
xitter.cf/LogConference/status/1โฆ
2) Join the first in-person conference from Sept 28-30 2025
xitter.cf/miniapeur/status/17907โฆ
Don't miss out on the opportunity to receive high-quality reviews!
LoG Conference 2024 is back !!!๐ We are looking for more reviewers! We have a special emphasis on review quality via monetary rewards, a more focused conference topic, and low reviewer load (max 3 papers). But for this we need your help! Sign up here: forms.gle/Nuff4ndVZDFTisb38!
The Graph Foundation Models Workshop @TheWebConf was a great success! We would like to extend a big thank you to our speakers, panelists, advisory board, organizers, and audience for making this event amazing!
Please visit our poster today (May 9), from 4:30 to 6:30 PM at Hall B, #89. See you there!
New paper w/ @he_xiaoxin, T. Laurent, @BryanHooi1 "Explanations as Features: LLM-Based Features for Text-Attributed Graphs"
ArXiv: arxiv.org/pdf/2305.19523.pdf
GitHub: github.com/XiaoxinHe/TAPE
๐ช๐๐๐ ๐๐๐๐ ๐๐๐๐ ๐ฎ๐๐๐๐ ๐ฃ๏ธ
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
ArXiv: arxiv.org/abs/2402.07630
GitHub: github.com/XiaoxinHe/G-Retriโฆ
BlogPost: medium.com/@xxhe/graph-retriโฆ
(5/n) We evaluate ๐ฎ-๐น๐๐๐๐๐๐๐๐ on our GraphQA benchmark, and consider three model configurations: 1) Inference-Only; 2) Frozen LLM + Prompt Tuning; and 3) Tuned LLM.
(6/n) If you are interested in related topics such as Graph RAG and Graph Prompt Tuning, please check out the 'Related Work and Discussion' section in our blog post: medium.com/@xxhe/graph-retriโฆ
