activity
20202025
most citedAn Investigation of how Label Smoothing Affects Generalization

8 citations · 52 across the 32 of their papers we have counts for

collaborators
Showing 2022Show all

8 papers · 1 filter

math.OC2022★ 3 cited

The Double Regularization Method for Capacity Constrained Optimal Transport

Tianhao Wu, Qihao Cheng, Zihao Wang +4

Capacity constrained optimal transport is a variant of optimal transport, which adds extra constraints on the set of feasible couplings in the original optimal transport problem to…

cs.CL2022★ 2 cited

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation

Ying Su, Zihao Wang, Tianqing Fang +3

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to…

cs.CL2022★ 4 cited

Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics

Zihao Wang, Jiaheng Dou, Yong Zhang

Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus…

math.OC2022

Fast Sinkhorn II: Collinear Triangular Matrix and Linear Time Accurate Computation of Optimal Transport

Qichen Liao, Zihao Wang, Jing Chen +3

In our previous work [arXiv:2202.10042], the complexity of Sinkhorn iteration is reduced from to the optimal by leveraging the special structure of the kernel matri…

cs.LG2022★ 5 cited

Posterior Collapse of a Linear Latent Variable Model

Zihao Wang, Liu Ziyin

This work identifies the existence and cause of a type of posterior collapse that frequently occurs in the Bayesian deep learning practice. For a general linear latent variable mod…

cs.CL2022

Query2Particles: Knowledge Graph Reasoning with Particle Embeddings

Jiaxin Bai, Zihao Wang, Hongming Zhang +1

Answering complex logical queries on incomplete knowledge graphs (KGs) with missing edges is a fundamental and important task for knowledge graph reasoning. The query embedding met…