The paper and source code of "Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem" (NAACL 2022) are available now. #NAACL2022 Paper📜: arxiv.org/abs/2205.01954 GitHub📂: github.com/joisino/wordto… x.com/joisino_en/sta…

Our paper "Re-evaluating Word Mover's Distance" was accepted to #ICML2022 as a long presentation🎉 We found simple bag-of-words perform close to Word Mover's Distance when normalized, and explored the reasons. Paper📜: arxiv.org/abs/2105.14403 Code📂: github.com/joisino/reeval…

My paper entitled "Active Learning from the Web" has been accepted to #TheWebConf (WWW) 🎉 I proposed a method for acquiring useful data for model training by regarding the myriad data on the web as a huge pool of active learning. Paper 📜： arxiv.org/abs/2210.08205

My paper "Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure" has been accepted to #ICML2023 🎉 I showed GNNs can create new and useful node features even when the input node features are uninformative. Paper📜 arxiv.org/abs/2301.10956

Survey slides on speeding up deep learning models are available‼️ speakerdeck.com/joisino/how-to…

Lecture slides on graph neural networks at #MLSS2024 are available ‼️ speakerdeck.com/joisino/introd…

A preprint is out. I proposed training-free graph neural networks. Check it out‼️ arxiv.org/abs/2404.19288

My paper "Making Translators Privacy-aware on the User’s Side" has been accepted to TMLR🎉 I proposed a method to guarantee privacy on the user's side when using an untrustworthy translator. Paper📜：arxiv.org/abs/2312.04068

I just published “The Hidden Information AI Understands but Humans Miss.” Check it out here: data-processing.club/superai/

🚀 Just published: A Gentle Introduction to Machine Learning Theory! data-processing.club/theory/

🚀 Just published: "Hack Your Feed: Take Control of Your Recommendations!" data-processing.club/consul/

🚀 Just published: "Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem!" data-processing.club/1dim/

📢NEWS: The Word Tour problem with 40,000 words has been solved optimally — thanks to the collaboration of William Cook and Keld Helsgaun! Details are updated on data-processing.club/1dim/ Solving such a large-scale NP-hard problem is truly remarkable!

Our paper "Influential Bandits: Pulling an Arm May Change the Environment" has been accepted to #TMLR 🎉 We proposed and analyzed the influential bandit problem, where an action affects the rewards of other actions. Paper📜：arxiv.org/abs/2504.08200

🚀 Just published: "Deceptive and Lazy AIs: When Language Models Learn to Mislead!" data-processing.club/mislead/