479 citations · 1.9k across the 94 of their papers we have counts for
25 papers · 1 filter
Baihe: SysML Framework for AI-driven Databases
Andreas Pfadler, Rong Zhu, Wei Chen +4
We present Baihe, a SysML Framework for AI-driven Databases. Using Baihe, an existing relational database system may be retrofitted to use learned components for query optimization…
Glue: Adaptively Merging Single Table Cardinality to Estimate Join Query Size
Rong Zhu, Tianjing Zeng, Andreas Pfadler +3
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS. The CardEst problem has been…
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
Jiangchao Yao, Shengyu Zhang, Yang Yao +15
Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the co…
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Junyang Lin, An Yang, Jinze Bai +9
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 a…
Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation
Yuxing Han, Ziniu Wu, Peizhi Wu +11
Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced…
VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition
Yang Li, Yu Shen, Wentao Zhang +8
End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algori…
Learning to Rehearse in Long Sequence Memorization
Zhu Zhang, Chang Zhou, Jianxin Ma +4
Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from…
Reliable Adversarial Distillation with Unreliable Teachers
Jianing Zhu, Jiangchao Yao, Bo Han +6
In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are…
Low-Rank Subspaces in GANs
Jiapeng Zhu, Ruili Feng, Yujun Shen +4
The latent space of a Generative Adversarial Network (GAN) has been shown to encode rich semantics within some subspaces. To identify these subspaces, researchers typically analyze…
Learning Relation Alignment for Calibrated Cross-modal Retrieval
Shuhuai Ren, Junyang Lin, Guangxiang Zhao +5
Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic ga…
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
Peng Wang, Junyang Lin, An Yang +4
Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from…
Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation
Yongji Wu, Defu Lian, Neil Zhenqiang Gong +4
Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-a…
Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
Yongji Wu, Lu Yin, Defu Lian +4
Sequential recommendation plays an increasingly important role in many e-commerce services such as display advertisement and online shopping. With the rapid development of these se…
TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
Lu Wang, Xiaofu Chang, Shuang Li +7
Dynamic graph modeling has recently attracted much attention due to its extensive applications in many real-world scenarios, such as recommendation systems, financial transactions,…
M6-T: Exploring Sparse Expert Models and Beyond
An Yang, Junyang Lin, Rui Men +12
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scal…
M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers
Zhu Zhang, Jianxin Ma, Chang Zhou +6
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as…
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Huangjie Zheng, Xu Chen, Jiangchao Yao +7
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative sampl…
A Unified Transferable Model for ML-Enhanced DBMS
Ziniu Wu, Pei Yu, Peilun Yang +6
Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. Despite their promising performance, these exis…
Device-Cloud Collaborative Learning for Recommendation
Jiangchao Yao, Feng Wang, KunYang Jia +3
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and…
M6: A Chinese Multimodal Pretrainer
Junyang Lin, Rui Men, An Yang +22
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We pro…
Dynamic Memory based Attention Network for Sequential Recommendation
Qiaoyu Tan, Jianwei Zhang, Ninghao Liu +4
Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and pre…
Sparse-Interest Network for Sequential Recommendation
Qiaoyu Tan, Jianwei Zhang, Jiangchao Yao +4
Recent methods in sequential recommendation focus on learning an overall embedding vector from a user's behavior sequence for the next-item recommendation. However, from empirical…
Inductive Granger Causal Modeling for Multivariate Time Series
Yunfei Chu, Xiaowei Wang, Jianxin Ma +3
Granger causal modeling is an emerging topic that can uncover Granger causal relationship behind multivariate time series data. In many real-world systems, it is common to encounte…
FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data
Shuyuan Yan, Bolin Ding, Wei Guo +4
Interactive response time is important in analytical pipelines for users to explore a sufficient number of possibilities and make informed business decisions. We consider a forecas…