Author name cluster

Yongjun Bao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

ICLR Conference 2025 Conference Paper

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

Leqi Shen
Tianxiang Hao 0001
Tao He
Sicheng Zhao
Yifeng Zhang
Pengzhang Liu
Yongjun Bao
Guiguang Ding

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting practical deployment. Addressing this, we focus on efficient text-video retrieval by tackling two key challenges: 1. From the perspective of trainable parameters, current parameter-efficient fine-tuning methods incur high inference costs; 2. From the perspective of model complexity, current token compression methods are mainly designed for images to reduce spatial redundancy but overlook temporal redundancy in consecutive frames of a video. To tackle these challenges, we propose Temporal Token Merging (TempMe), a parameter-efficient and training-inference efficient text-video retrieval architecture that minimizes trainable parameters and model complexity. Specifically, we introduce a progressive multi-granularity framework. By gradually combining neighboring clips, we reduce spatio-temporal redundancy and enhance temporal modeling across different frames, leading to improved efficiency and performance. Extensive experiments validate the superiority of our TempMe. Compared to previous parameter-efficient text-video retrieval methods, TempMe achieves superior performance with just 0.50M trainable parameters. It significantly reduces output tokens by 95% and GFLOPs by 51%, while achieving a 1.8X speedup and a 4.4% R-Sum improvement. With full fine-tuning, TempMe achieves a significant 7.9% R-Sum improvement, trains 1.57X faster, and utilizes 75.2% GPU memory usage. The code is available at https://github.com/LunarShen/TempMe.

Details

AAAI Conference 2024 Conference Paper

Patch-Aware Sample Selection for Efficient Masked Image Modeling

Zhengyang Zhuge
Jiaxing Wang
Yong Li
Yongjun Bao
Peisong Wang
Jian Cheng

Nowadays sample selection is drawing increasing attention. By extracting and training only on the most informative subset, sample selection can effectively reduce the training cost. Although sample selection is effective in conventional supervised learning, applying it to Masked Image Modeling (MIM) still poses challenges due to the gap between sample-level selection and patch-level pre-training. In this paper, we inspect the sample selection in MIM pre-training and find the basic selection suffers from performance degradation. We attribute this degradation primarily to 2 factors: the random mask strategy and the simple averaging function. We then propose Patch-Aware Sample Selection (PASS), including a low-cost Dynamic Trained Mask Predictor (DTMP) and Weighted Selection Score (WSS). DTMP consistently masks the informative patches in samples, ensuring a relatively accurate representation of selection score. WSS enhances the selection score using patch-level disparity. Extensive experiments show the effectiveness of PASS in selecting the most informative subset and accelerating pretraining. PASS exhibits superior performance across various datasets, MIM methods, and downstream tasks. Particularly, PASS improves MAE by 0.7% on ImageNet-1K while utilizing only 37% data budget and achieves ~1.7x speedup.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

TaD: A Plug-and-Play Task-Aware Decoding Method to Better Adapt LLMs on Downstream Tasks

Xinhao Xu
Hui Chen
Zijia Lin
Jungong Han
Lixing Gong
Guoxin Wang
Yongjun Bao
Guiguang Ding

Fine-tuning pre-trained models on downstream tasks is a common practice in leveraging large language models (LLMs) today. A critical issue is how to adapt pre-trained models to downstream tasks better, thereby enhancing their performance. This paper introduces Task-aware Decoding (TaD), a plug-and-play method that exploits the difference in probability distributions before and after fine-tuning to boost the performance of LLMs on downstream tasks. The proposed TaD argues that the difference between the pre-finetuning probability distribution and the post-finetuning one represents the direction from common knowledge towards specific downstream-task knowledge. Aligning the final output probability distribution to that direction can probably result in superior downstream task performance, compared to the original fine-tuned model. Experiments on various datasets across four different task categories well demonstrate TaD's effectiveness on different LLMs, i. e. , GPT, BLOOM, and LLaMA, with different fine-tuning methods. Moreover, further experiments reveal that TaD better enhances model performance in data-scarce scenarios.

PDF Details DOI

ICLR Conference 2023 Conference Paper

DynaMS: Dyanmic Margin Selection for Efficient Deep Learning

Jiaxing Wang
Yong Li
Jingwei Zhuo
Xupeng Shi
Weizhong Zhang
Lixing Gong
Tong Tao
Pengzhang Liu

The great success of deep learning is largely driven by training over-parameterized models on massive datasets. To avoid excessive computation, extracting and training only on the most informative subset is drawing increasing attention. Nevertheless, it is still an open question how to select such a subset on which the model trained generalizes on par with the full data. In this paper, we propose dynamic margin selection (DynaMS). DynaMS leverages the distance from candidate samples to the classification boundary to construct the subset, and the subset is dynamically updated during model training. We show that DynaMS converges with large probability, and for the first time show both in theory and practice that dynamically updating the subset can result in better generalization over previous works. To reduce the additional computation incurred by the selection, a light parameter sharing proxy (PSP) is designed. PSP is able to faithfully evaluate instances with respect to the current model, which is necessary for dynamic selection. Extensive analysis and experiments demonstrate the superiority of the proposed approach in data selection against many state-of-the-art counterparts on benchmark datasets.

Details

AAAI Conference 2021 Conference Paper

Probing Product Description Generation via Posterior Distillation

Haolan Zhan
Hainan Zhang
Hongshen Chen
Lei Shen
Zhuoye Ding
Yongjun Bao
Weipeng Yan
Yanyan Lan

In product description generation (PDG), the user-cared aspect is critical for the recommendation system, which can not only improve user’s experiences but also obtain more clicks. High-quality customer reviews can be considered as an ideal source to mine user-cared aspects. However, in reality, a large number of new products (known as long-tailed commodities) cannot gather sufficient amount of customer reviews, which brings a big challenge in the product description generation task. Existing works tend to generate the product description solely based on item information, i. e. , product attributes or title words, which leads to tedious contents and cannot attract customers effectively. To tackle this problem, we propose an adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews. Specifically, we first extend the selfattentive Transformer encoder to encode product titles and attributes. Then, we apply an adaptive posterior distillation module to utilize useful review information, which integrates user-cared aspects to the generation process. Finally, we apply a Transformer-based decoding phase with copy mechanism to automatically generate the product description. Besides, we also collect a large-scare Chinese product description dataset to support our work and further research in this field. Experimental results show that our model is superior to traditional generative models in both automatic indicators and human evaluation.

PDF Details

IJCAI Conference 2020 Conference Paper

An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration

Yumin Su
Liang Zhang
Quanyu Dai
Bo Zhang
Jinyao Yan
Dan Wang
Yongjun Bao
Sulong Xu

Conversion rate (CVR) prediction is becoming increasingly important in the multi-billion dollar online display advertising industry. It has two major challenges: firstly, the scarce user history data is very complicated and non-linear; secondly, the time delay between the clicks and the corresponding conversions can be very large, e. g. , ranging from seconds to weeks. Existing models usually suffer from such scarce and delayed conversion behaviors. In this paper, we propose a novel deep learning framework to tackle the two challenges. Specifically, we extract the pre-trained embedding from impressions/clicks to assist in conversion models and propose an inner/self-attention mechanism to capture the fine-grained personalized product purchase interests from the sequential click data. Besides, to overcome the time-delay issue, we calibrate the delay model by learning dynamic hazard function with the abundant post-click data more in line with the real distribution. Empirical experiments with real-world user behavior data prove the effectiveness of the proposed method.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Hu Liu
Jing Lu
Xiwei Zhao
Sulong Xu
Hao Peng
Yutong Liu
Zehua Zhang
Jian Li

Click-through rate (CTR) prediction is one of the fundamental tasks for e-commerce search engines. As search becomes more personalized, it is necessary to capture the user interest from rich behavior data. Existing user behavior modeling algorithms develop different attention mechanisms to emphasize query-relevant behaviors and suppress irrelevant ones. Despite being extensively studied, these attentions still suffer from two limitations. First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors. Second, these attentions are usually biased towards frequent behaviors, which is unreasonable since high frequency does not necessarily indicate great importance. To tackle the two limitations, we propose a novel attention mechanism, termed Kalman Filtering Attention (KFAtt), that considers the weighted pooling in attention as a maximum a posteriori (MAP) estimation. By incorporating a priori, KFAtt resorts to global statistics when few user behaviors are relevant. Moreover, a frequency capping mechanism is incorporated to correct the bias towards frequent behaviors. Offline experiments on both benchmark and a 10 billion scale real production dataset, together with an Online A/B test, show that KFAtt outperforms all compared state-of-the-arts. KFAtt has been deployed in the ranking system of JD. com, one of the largest B2C e-commerce websites in China, serving the main traffic of hundreds of millions of active users.

PDF Details