no code implementations • 31 Mar 2024 • Hao Gong, Michel Desvignes
Decomposition of skin pigment plays an important role in medical fields.
no code implementations • 14 Feb 2022 • Tianyu Li, Ali Cevahir, Derek Cho, Hao Gong, DuyKhuong Nguyen, Bjorn Stenger
This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner.
no code implementations • 1 Jan 2021 • Tianyu Li, Ali Cevahir, Derek Cho, Hao Gong, DuyKhuong Nguyen, Bjorn Stenger
This paper extends the BERT model to user data for pretraining user representations in a self-supervised way.
no code implementations • 21 Aug 2020 • Hao Gong, Qifang Zhao, Tianyu Li, Derek Cho, DuyKhuong Nguyen
1) Meta-learning model: In the context of representation learning with e-commerce user behavior data, we propose a meta-learning framework called the Meta-Profile Network, which extends the ideas of matching network and relation network for knowledge transfer and fast adaptation; 2) Encoding strategy: To keep high fidelity of large-scale long-term sequential behavior data, we propose a time-heatmap encoding strategy that allows the model to encode data effectively; 3) Deep network architecture: A multi-modal model combined with multi-task learning architecture is utilized to address the cross-domain knowledge learning and insufficient label problems.
no code implementations • L4DC 2020 • Hao Gong, Mengdi Wang
In light of the Bellman duality, we propose a novel value-policy gradient algorithm to explore and act in infinite-horizon Average-reward Markov Decision Process (AMDP) and show that it has sublinear regret.
no code implementations • NeurIPS 2019 • Yifan Sun, Yaqi Duan, Hao Gong, Mengdi Wang
This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank.