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

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

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

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

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

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

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…

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…

I created a fill-in-the-blank game with paper abstracts. Let's try BERT's job! 👉 pretrain-yourself.joisino.net

'Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data?' will appear at #SIAMSDM22

We consider how a user of a web service can build their own recommender system.

📜Paper: arxiv.org/abs/2105.12353
📂Github: github.com/joisino/privat…

One paper entitled 'Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem' has been accepted to #NAACL2022 (main conference, short paper) 🎉

Our paper entitled 'Poincare: Recommending Publication Venues via Treatment Effect Estimation' has been accepted to Journal of Informetrics 🎉 Our proposed method suggests where you should publish your paper to attract attention. arxiv.org/abs/2010.09157

Our paper 'Fixed Support Tree-Sliced Wasserstein Barycenter' has been accepted to #AISTATS2022 🎉 arxiv.org/abs/2109.03431

One paper entitled 'Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data?' has been accepted to #SIAMSDM22 🎉 arxiv.org/abs/2105.12353

Our paper 'Constant Time Graph Neural Networks' has been accepted to TKDD 🎉 arXiv: arxiv.org/abs/1901.07868

2. Retrieving Black-box Optimal Images from External Databases #WSDM2022 (arXiv TBA) We propose a method for retrieving desired images via search APIs. Our method can realize a similar image search and image recommendations even if the service does not offer such functions.