Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Zhuo, Jingwei"'
Autor:
Kuai, Zhirui, Chen, Zuxu, Wang, Huimu, Li, Mingming, Miao, Dadong, Wang, Binbin, Chen, Xusong, Kuang, Li, Han, Yuxing, Wang, Jiaxing, Tang, Guoyu, Liu, Lin, Wang, Songlin, Zhuo, Jingwei
Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing Residual Quantiz
Externí odkaz:
http://arxiv.org/abs/2407.21488
Autor:
Li, Mingming, Wang, Huimu, Chen, Zuxu, Nie, Guangtao, Qiu, Yiming, Wang, Binbin, Tang, Guoyu, Liu, Lin, Zhuo, Jingwei
Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and potential, particu
Externí odkaz:
http://arxiv.org/abs/2407.19829
Autor:
Wang, Binbin, Li, Mingming, Zeng, Zhixiong, Zhuo, Jingwei, Wang, Songlin, Xu, Sulong, Long, Bo, Yan, Weipeng
Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework to learn
Externí odkaz:
http://arxiv.org/abs/2303.11009
Autor:
Qiu, Yiming, Zhao, Chenyu, Zhang, Han, Zhuo, Jingwei, Li, Tianhao, Zhang, Xiaowei, Wang, Songlin, Xu, Sulong, Long, Bo, Yang, Wen-Yun
BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. Ho
Externí odkaz:
http://arxiv.org/abs/2208.06150
Learning the user-item relevance hidden in implicit feedback data plays an important role in modern recommender systems. Neural sequential recommendation models, which formulates learning the user-item relevance as a sequential classification problem
Externí odkaz:
http://arxiv.org/abs/2202.13616
Retrieving relevant targets from an extremely large target set under computational limits is a common challenge for information retrieval and recommendation systems. Tree models, which formulate targets as leaves of a tree with trainable node-wise sc
Externí odkaz:
http://arxiv.org/abs/2006.15408
It is known that the Langevin dynamics used in MCMC is the gradient flow of the KL divergence on the Wasserstein space, which helps convergence analysis and inspires recent particle-based variational inference methods (ParVIs). But no more MCMC dynam
Externí odkaz:
http://arxiv.org/abs/1902.00282
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations. We explore ParVIs from the perspective of Wasserstein gradient flows,
Externí odkaz:
http://arxiv.org/abs/1807.01750
The kernel embedding algorithm is an important component for adapting kernel methods to large datasets. Since the algorithm consumes a major computation cost in the testing phase, we propose a novel teacher-learner framework of learning computation-e
Externí odkaz:
http://arxiv.org/abs/1712.02527
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational i
Externí odkaz:
http://arxiv.org/abs/1711.04425