143 citations
- Institut de recherche mathématique de RennesFR2 papers
- SMART ReadingUS2 papers
- University of California, RiversideUS2 papers
- University of Wisconsin–MadisonUS2 papers
- Amazon (United States)US1 paper
- Arizona State UniversityUS1 paper
- École nationale des ponts et chausséesFR1 paper
- Santa Clara UniversityUS1 paper
- Science ClubUS1 paper
- Technion – Israel Institute of TechnologyIL1 paper
- Texas A&M UniversityUS1 paper
- University of Illinois ChicagoUS1 paper
6 papers · 1 filter
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
Ye Yuan, Wuyang Chen, Yang Yang +1
The comparative losses (typically, triplet loss) are appealing choices for learning person re-identification (ReID) features. However, the triplet loss is computationally much more…
Self-attention with Functional Time Representation Learning
Da Xu, Chuanwei Ruan, Sushant Kumar +2
Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and int…
Product Knowledge Graph Embedding for E-commerce
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
In this paper, we propose a new product knowledge graph (PKG) embedding approach for learning the intrinsic product relations as product knowledge for e-commerce. We define the key…
Generative Graph Convolutional Network for Growing Graphs
Da Xu, Chuanwei Ruan, Kamiya Motwani +3
Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existin…
Signed Link Prediction with Sparse Data: The Role of Personality Information
Ghazaleh Beigi, Suhas Ranganath, Huan Liu
Predicting signed links in social networks often faces the problem of signed link data sparsity, i.e., only a small percentage of signed links are given. The problem is exacerbated…
On Application of Learning to Rank for E-Commerce Search
Shubhra Kanti Karmaker Santu, Parikshit Sondhi, ChengXiang Zhai
E-Commerce (E-Com) search is an emerging important new application of information retrieval. Learning to Rank (LETOR) is a general effective strategy for optimizing search engines,…