no code implementations • 14 Sep 2023 • Pu Miao, Zeyao Du, Junlin Zhang
Contrastive learning schemes such as SimCSE and ConSERT have already been adopted successfully in unsupervised sentence embedding to improve the quality of embeddings by reducing this bias.
2 code implementations • NeurIPS 2023 • Viorica Pătrăucean, Lucas Smaira, Ankush Gupta, Adrià Recasens Continente, Larisa Markeeva, Dylan Banarse, Skanda Koppula, Joseph Heyward, Mateusz Malinowski, Yi Yang, Carl Doersch, Tatiana Matejovicova, Yury Sulsky, Antoine Miech, Alex Frechette, Hanna Klimczak, Raphael Koster, Junlin Zhang, Stephanie Winkler, Yusuf Aytar, Simon Osindero, Dima Damen, Andrew Zisserman, João Carreira
We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e. g. Flamingo, SeViLA, or GPT-4).
1 code implementation • 25 Oct 2022 • PengTao Zhang, Junlin Zhang
In this paper, we propose multi-Hash Codebook NETwork (HCNet) as the memory mechanism for efficiently learning and memorizing representations of cross features in CTR tasks.
Ranked #1 on Click-Through Rate Prediction on KDD12
1 code implementation • Deep Mind 2022 • Viorica Pătrăucean, Lucas Smaira, Ankush Gupta, Adrià Recasens Continente, Larisa Markeeva, Dylan Banarse, Mateusz Malinowski, Yi Yang, Carl Doersch, Tatiana Matejovicova, Yury Sulsky, Antoine Miech, Skanda Koppula, Alex Frechette, Hanna Klimczak, Raphael Koster, Junlin Zhang, Stephanie Winkler, Yusuf Aytar, Simon Osindero, Dima Damen, Andrew Zisserman and João Carreira
We propose a novel multimodal benchmark – the Perception Test – that aims to extensively evaluate perception and reasoning skills of multimodal models.
4 code implementations • 12 Sep 2022 • PengTao Zhang, Zheng Zheng, Junlin Zhang
Click-Through Rate (CTR) estimation has become one of the most fundamental tasks in many real-world applications and various deep models have been proposed.
Ranked #16 on Click-Through Rate Prediction on Criteo
no code implementations • 26 Jul 2021 • Qingyun She, Zhiqiang Wang, Junlin Zhang
For example, the continuous features are usually transformed to the power forms by adding a new feature to allow it to easily form non-linear functions of the feature.
3 code implementations • 26 Jul 2021 • Zhiqiang Wang, Qingyun She, PengTao Zhang, Junlin Zhang
In this paper, We propose a novel CTR Framework named ContextNet that implicitly models high-order feature interactions by dynamically refining each feature's embedding according to the input context.
Ranked #15 on Click-Through Rate Prediction on Criteo
15 code implementations • 9 Feb 2021 • Zhiqiang Wang, Qingyun She, Junlin Zhang
We also turn the feed-forward layer in DNN model into a mixture of addictive and multiplicative feature interactions by proposing MaskBlock in this paper.
Ranked #9 on Click-Through Rate Prediction on Criteo
no code implementations • 13 Sep 2020 • Tongwen Huang, Qingyun She, Junlin Zhang
Our proposed model uses the pre-trained Transformer as the base classifier to choose harder training sets to fine-tune and gains the benefits of both the pre-training language knowledge and boosting ensemble in NLP tasks.
3 code implementations • 6 Jul 2020 • Tongwen Huang, Qingyun She, Zhiqiang Wang, Junlin Zhang
Inspired by these observations, we propose a novel model named GateNet which introduces either the feature embedding gate or the hidden gate to the embedding layer or hidden layers of DNN CTR models, respectively.
Ranked #21 on Click-Through Rate Prediction on Criteo
1 code implementation • 23 Jun 2020 • Zhiqiang Wang, Qingyun She, PengTao Zhang, Junlin Zhang
Normalization has become one of the most fundamental components in many deep neural networks for machine learning tasks while deep neural network has also been widely used in CTR estimation field.
31 code implementations • 23 May 2019 • Tongwen Huang, Zhiqi Zhang, Junlin Zhang
In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions.
Ranked #19 on Click-Through Rate Prediction on Criteo
12 code implementations • 15 May 2019 • Junlin Zhang, Tongwen Huang, Zhiqi Zhang
Although some CTR model such as Attentional Factorization Machine (AFM) has been proposed to model the weight of second order interaction features, we posit the evaluation of feature importance before explicit feature interaction procedure is also important for CTR prediction tasks because the model can learn to selectively highlight the informative features and suppress less useful ones if the task has many input features.
Ranked #18 on Click-Through Rate Prediction on Criteo
no code implementations • 29 Sep 2016 • Lei Shen, Junlin Zhang
Recurrent Neural Networks have achieved state-of-the-art results for many problems in NLP and two most popular RNN architectures are Tail Model and Pooling Model.
no code implementations • 23 Mar 2015 • Junlin Zhang, Jose Garcia
To solve this problem, we propose to learn a new classifier by adding an adaptation function to the base classifier, and update the adaptation function parameter according to the streaming data samples.