Liwei Wang

Groupwise Bayesian dimension reduction

2017

Nearly all existing estimations of the central subspace in regression take the frequentist approach. However, when the predictors fall naturally into a number of groups, these frequentist methods treat all predictors indiscriminately and can result …

Field implementation of long-distance quantum key distribution over aerial fiber with fast polarization feedback

2018 · Optics Express

Quantum key distribution with polarized qubits has not yet been realized over the aerial fiber, due to rapid polarization changes. Here, we report our recent work towards quantum communication through an aerial fiber channel. We …

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

2019 · arXiv (Cornell University)

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs. In this paper, we …

McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds

2019 · arXiv (Cornell University)

A crucial assumption in most statistical learning theory is that samples are independently and identically distributed (i.i.d.). However, for many real applications, the i.i.d. assumption does not hold. We consider learning problems in which examples …

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

2020 · arXiv (Cornell University)

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversarial …

MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning

2023

Yongfeng Huang, Yanyang Li, Yichong Xu, Lin Zhang, Ruyi Gan, Jiaxing Zhang, Liwei Wang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Hierarchical Federated Learning for Social Network with Mobility

2025 · arXiv (Cornell University)

Federated Learning (FL) offers a decentralized solution that allows collaborative local model training and global aggregation, thereby protecting data privacy. In conventional FL frameworks, data privacy is typically preserved under the assumption that local data …

Dual Learning for Machine Translation

2016 · arXiv (Cornell University)

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this …