Haoyu Han (@HaoyuHan) profile picture

CS PhD student in MSU

East Lansing, MI
Joined January 2016
Photo by Haoyu Han (@HaoyuHan)
📢 CFP: The 3rd LLM4ECommerce Workshop @ #WSDM2027! 🇭🇰 Feb 19, 2027 | Hong Kong 📝 Deadline: Nov 30 (AoE) We welcome research on LLMs for e-commerce, including search, recommendation, personalization, RAG, multimodal LLMs, agents & more! 🔗 llm4ecommerce.github.io/
🤖 Made with AI
1
1
34
Haoyu Han retweeted
An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation Airbnb shows that a simple graph heuristic matches or beats modern generative recommenders on popular benchmarks. 📝 arxiv.org/abs/2605.07125 👨🏽‍💻 github.com/haoyuhan1/GraphRe…
4
1
17
2,072
📢Call for Papers: LLM for E-Commerce Workshop @ WWW'25 📅April 28-29, 2025 | Sydney, Australia 🌍 Explore how LLMs are transforming e-commerce: foundations, applications & systems. 📝Submit: openreview.net/group?id=ACM.… (by Jan 26, 2025 AoE) 👉Details: llm4ecommerce.github.io/
3
739
🔍 Key Highlights: ✅ A holistic GraphRAG framework ✅ Domain-specific techniques and insights (knowledge graphs, document graphs, molecular graphs & more) ✅ Challenges and Future directions 📝 Read the full survey here: arxiv.org/abs/2501.00309v1 #Graphs #RAG #MachineLearning
3
6
839
🚀 Excited to announce our new survey on Retrieval-Augmented Generation with Graphs (GraphRAG)! How do graphs transform Retrieval-Augmented Generation(RAG)? By encoding relational and domain knowledge, GraphRAG is unlocking new possibilities across real-world applications! 🌐
1
3
4
657
Join us for an exciting tutorial on Large-Scale Graph Neural Networks at #KDD2023 !! We delve into not only classic scaling approaches but also the latest intriguing and promising emerging techniques in the field. 📅 Time: 2:00 pm - 5:00 pm, August 9th 📍 Location: Room 202C
3
22
1,684
Our #NeurIPS2021 paper “Graph Neural Networks with Adaptive Residual” proposes an effective GNN architecture with adaptive residuals based on local consistency. It significantly improves the robustness against abnormal features. Welcome to check our paper and visit the poster.
1
16
1
84