no code implementations • 14 Jan 2025 • Feijie Wu, Zitao Li, Fei Wei, Yaliang Li, Bolin Ding, Jing Gao
Experimental results demonstrate that RopMura effectively handles both single-hop and multi-hop queries, with the routing mechanism enabling precise answers for single-hop queries and the combined routing and planning mechanisms achieving accurate, multi-step resolutions for complex queries.
1 code implementation • 23 Dec 2024 • Daoyuan Chen, Yilun Huang, Xuchen Pan, Nana Jiang, Haibin Wang, Ce Ge, Yushuo Chen, WenHao Zhang, Zhijian Ma, Yilei Zhang, Jun Huang, Wei Lin, Yaliang Li, Bolin Ding, Jingren Zhou
The burgeoning field of foundation models necessitates advanced data processing mechanisms capable of harnessing vast valuable data with varied types utilized by these models.
1 code implementation • 23 Dec 2024 • Ting Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding, Yaliang Li, Ying Shen
In the domain of Multimodal Large Language Models (MLLMs), achieving human-centric video understanding remains a formidable challenge.
no code implementations • 29 Nov 2024 • Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou
We propose a general two-stage algorithm that enjoys a provable scaling law for the test-time compute of large language models (LLMs).
1 code implementation • 31 Oct 2024 • Lizhe Fang, Yifei Wang, Zhaoyang Liu, Chenheng Zhang, Stefanie Jegelka, Jinyang Gao, Bolin Ding, Yisen Wang
To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them.
1 code implementation • 18 Oct 2024 • Pengfei He, Zitao Li, Yue Xing, Yaling Li, Jiliang Tang, Bolin Ding
In this paper, we address this limitation by introducing a novel structure-oriented analysis method to help LLMs better understand the question and guide the problem-solving process of LLMs.
1 code implementation • 14 Oct 2024 • Junkang Wu, Xue Wang, Zhengyi Yang, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He
Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety.
1 code implementation • 13 Oct 2024 • Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding
The structural properties of naturally arising social graphs are extensively studied to understand their evolution.
1 code implementation • 6 Oct 2024 • Jiakai Tang, Heyang Gao, Xuchen Pan, Lei Wang, Haoran Tan, Dawei Gao, Yushuo Chen, Xu Chen, Yankai Lin, Yaliang Li, Bolin Ding, Jingren Zhou, Jun Wang, Ji-Rong Wen
With the rapid advancement of large language models (LLMs), recent years have witnessed many promising studies on leveraging LLM-based agents to simulate human social behavior.
1 code implementation • 3 Oct 2024 • Ao Li, Yuexiang Xie, Songze Li, Fugee Tsung, Bolin Ding, Yaliang Li
Through the collaboration of multiple agents possessing diverse expertise and tools, multi-agent systems achieve impressive progress in solving real-world problems.
1 code implementation • 28 Aug 2024 • Yuchang Sun, Yuexiang Xie, Bolin Ding, Yaliang Li, Jun Zhang
Federated learning (FL) has emerged as a promising paradigm for fine-tuning foundation models using distributed data in a privacy-preserving manner.
1 code implementation • 12 Aug 2024 • Fangyuan Zhao, Yuexiang Xie, Xuebin Ren, Bolin Ding, Shusen Yang, Yaliang Li
Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates.
no code implementations • 8 Aug 2024 • Qirui Jiao, Daoyuan Chen, Yilun Huang, Bolin Ding, Yaliang Li, Ying Shen
We release our codes and dataset to encourage further research on multimodal data synthesis and MLLMs' fundamental capabilities for image understanding.
Ranked #87 on
Visual Question Answering
on MM-Vet
1 code implementation • 25 Jul 2024 • Xuchen Pan, Dawei Gao, Yuexiang Xie, Yushuo Chen, Zhewei Wei, Yaliang Li, Bolin Ding, Ji-Rong Wen, Jingren Zhou
Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations.
1 code implementation • 20 Jul 2024 • Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou
We initiate a formal investigation into the design and analysis of LLM-based algorithms, i. e. algorithms that contain one or multiple calls of large language models (LLMs) as sub-routines and critically rely on the capabilities of LLMs.
1 code implementation • 16 Jul 2024 • Daoyuan Chen, Haibin Wang, Yilun Huang, Ce Ge, Yaliang Li, Bolin Ding, Jingren Zhou
The emergence of large-scale multi-modal generative models has drastically advanced artificial intelligence, introducing unprecedented levels of performance and functionality.
1 code implementation • 11 Jul 2024 • Zhen Qin, Daoyuan Chen, WenHao Zhang, Liuyi Yao, Yilun Huang, Bolin Ding, Yaliang Li, Shuiguang Deng
As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition.
1 code implementation • 11 Jul 2024 • Junkang Wu, Yuexiang Xie, Zhengyi Yang, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He
Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences.
1 code implementation • 10 Jul 2024 • Junkang Wu, Yuexiang Xie, Zhengyi Yang, Jiancan Wu, Jiawei Chen, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He
We categorize noise into pointwise noise, which includes low-quality data points, and pairwise noise, which encompasses erroneous data pair associations that affect preference rankings.
1 code implementation • 25 Jun 2024 • Feijie Wu, Zitao Li, Yaliang Li, Bolin Ding, Jing Gao
Specifically, our method involves the server generating a compressed LLM and aligning its performance with the full model.
1 code implementation • 3 Jun 2024 • Tianjing Zeng, Junwei Lan, Jiahong Ma, Wenqing Wei, Rong Zhu, Pengfei Li, Bolin Ding, Defu Lian, Zhewei Wei, Jingren Zhou
It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods.
no code implementations • 23 May 2024 • Ce Ge, Zhijian Ma, Daoyuan Chen, Yaliang Li, Bolin Ding
Optimization of domain proportions yields superior model performance compared to existing methods.
no code implementations • 10 May 2024 • Yichen Qian, Yongyi He, Rong Zhu, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian, Bolin Ding, Jingren Zhou
In this paper, inspired by the cross-task generality of LLMs on NLP tasks, we pave the first step to design an automatic and general solution to tackle with data manipulation tasks.
1 code implementation • 26 Apr 2024 • Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, HuaWei Shen, Bolin Ding
Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality.
no code implementations • 18 Mar 2024 • Youbang Sun, Zitao Li, Yaliang Li, Bolin Ding
Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models for its good performance and computational efficiency.
no code implementations • 23 Feb 2024 • Yue Cui, Liuyi Yao, Zitao Li, Yaliang Li, Bolin Ding, Xiaofang Zhou
We analyze the proposed bargaining model under perfect and imperfect performance information settings, proving the existence of an equilibrium that optimizes the parties' objectives.
1 code implementation • 21 Feb 2024 • Dawei Gao, Zitao Li, Xuchen Pan, Weirui Kuang, Zhijian Ma, Bingchen Qian, Fei Wei, WenHao Zhang, Yuexiang Xie, Daoyuan Chen, Liuyi Yao, Hongyi Peng, Zeyu Zhang, Lin Zhu, Chen Cheng, Hongzhu Shi, Yaliang Li, Bolin Ding, Jingren Zhou
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications.
no code implementations • 5 Feb 2024 • Yuan Gao, Haokun Chen, Xiang Wang, Zhicai Wang, Xue Wang, Jinyang Gao, Bolin Ding
Our research demonstrates the efficacy of leveraging AIGS and the DiffsFormer architecture to mitigate data scarcity in stock forecasting tasks.
no code implementations • 2 Feb 2024 • Yue Cui, Liuyi Yao, Yaliang Li, Ziqian Chen, Bolin Ding, Xiaofang Zhou
This FL market allows clients to gain monetary reward by selling their own models and improve local model performance through the purchase of others' models.
1 code implementation • 1 Feb 2024 • Xuchen Pan, Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou
This work introduces EE-Tuning, a lightweight and economical solution to training/tuning early-exit large language models (LLMs).
no code implementations • 9 Jan 2024 • Ke Zhang, Lichao Sun, Bolin Ding, Siu Ming Yiu, Carl Yang
Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications.
2 code implementations • 11 Dec 2023 • Zhen Qin, Daoyuan Chen, Bingchen Qian, Bolin Ding, Yaliang Li, Shuiguang Deng
Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions.
1 code implementation • 8 Dec 2023 • Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou
We present EE-LLM, a framework for large-scale training and inference of early-exit large language models (LLMs).
1 code implementation • 12 Nov 2023 • Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, Yaliang Li
As the global model itself is not required to be shared and the local training is conducted based on an auxiliary model with fewer parameters than the global model, the proposed approach provides protection for the global model while reducing communication and computation costs in FL.
2 code implementations • 5 Sep 2023 • Daoyuan Chen, Yilun Huang, Zhijian Ma, Hesen Chen, Xuchen Pan, Ce Ge, Dawei Gao, Yuexiang Xie, Zhaoyang Liu, Jinyang Gao, Yaliang Li, Bolin Ding, Jingren Zhou
A data recipe is a mixture of data from different sources for training LLMs, which plays a vital role in LLMs' performance.
1 code implementation • 1 Sep 2023 • Weirui Kuang, Bingchen Qian, Zitao Li, Daoyuan Chen, Dawei Gao, Xuchen Pan, Yuexiang Xie, Yaliang Li, Bolin Ding, Jingren Zhou
When several entities have similar interested tasks, but their data cannot be shared because of privacy concerns regulations, federated learning (FL) is a mainstream solution to leverage the data of different entities.
1 code implementation • 29 Aug 2023 • Dawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun, Yichen Qian, Bolin Ding, Jingren Zhou
Our explorations highlight open-source LLMs' potential in Text-to-SQL, as well as the advantages and disadvantages of the supervised fine-tuning.
Ranked #3 on
Text-To-SQL
on spider
1 code implementation • 16 Jul 2023 • Peiyu Liu, Zikang Liu, Ze-Feng Gao, Dawei Gao, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen
Different from previous studies focused on overall performance, this work aims to investigate the impact of quantization on \emph{emergent abilities}, which are important characteristics that distinguish LLMs from small language models.
no code implementations • 5 Jul 2023 • Yuzheng Hu, Fan Wu, Qinbin Li, Yunhui Long, Gonzalo Munilla Garrido, Chang Ge, Bolin Ding, David Forsyth, Bo Li, Dawn Song
As the prevalence of data analysis grows, safeguarding data privacy has become a paramount concern.
1 code implementation • 20 May 2023 • Wang Xue, Tian Zhou, Qingsong Wen, Jinyang Gao, Bolin Ding, Rong Jin
In this work, we design a special Transformer, i. e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting.
2 code implementations • 4 May 2023 • Daoyuan Chen, Liuyi Yao, Dawei Gao, Bolin Ding, Yaliang Li
To overcome these challenges, we propose a novel approach named pFedGate for efficient personalized FL by adaptively and efficiently learning sparse local models.
no code implementations • 23 Mar 2023 • Daoyuan Chen, Dawei Gao, Yuexiang Xie, Xuchen Pan, Zitao Li, Yaliang Li, Bolin Ding, Jingren Zhou
Federated Learning (FL) aims to train high-quality models in collaboration with distributed clients while not uploading their local data, which attracts increasing attention in both academia and industry.
1 code implementation • 14 Feb 2023 • Rong Zhu, Wei Chen, Bolin Ding, Xingguang Chen, Andreas Pfadler, Ziniu Wu, Jingren Zhou
In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance.
1 code implementation • 3 Feb 2023 • Zeyu Qin, Liuyi Yao, Daoyuan Chen, Yaliang Li, Bolin Ding, Minhao Cheng
We conduct the first study of backdoor attacks in the pFL framework, testing 4 widely used backdoor attacks against 6 pFL methods on benchmark datasets FEMNIST and CIFAR-10, a total of 600 experiments.
1 code implementation • 12 Dec 2022 • Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, Yaliang Li
In this study, we further broaden the application scope of FL in NLP by proposing an Assign-Then-Contrast (denoted as ATC) framework, which enables clients with heterogeneous NLP tasks to construct an FL course and learn useful knowledge from each other.
2 code implementations • 13 Jun 2022 • Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen
In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors.
1 code implementation • 8 Jun 2022 • Daoyuan Chen, Dawei Gao, Weirui Kuang, Yaliang Li, Bolin Ding
Personalized Federated Learning (pFL), which utilizes and deploys distinct local models, has gained increasing attention in recent years due to its success in handling the statistical heterogeneity of FL clients.
1 code implementation • 8 Jun 2022 • Zhen Wang, Weirui Kuang, Ce Zhang, Bolin Ding, Yaliang Li
Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting.
1 code implementation • 7 Jun 2022 • Liuyi Yao, Dawei Gao, Zhen Wang, Yuexiang Xie, Weirui Kuang, Daoyuan Chen, Haohui Wang, Chenhe Dong, Bolin Ding, Yaliang Li
To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federated learning in terms of both data distribution and learning tasks.
no code implementations • 6 Jun 2022 • Shanlei Mu, Yupeng Hou, Wayne Xin Zhao, Yaliang Li, Bolin Ding
Instead of explicitly learning representations for item IDs, IDA-SR directly learns item representations from rich text information.
1 code implementation • 27 May 2022 • Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei
Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs, rendering these models vulnerable to graph structural attacks and with limited capacity in generalizing to graphs of varied homophily levels.
1 code implementation • 12 Apr 2022 • Zhen Wang, Weirui Kuang, Yuexiang Xie, Liuyi Yao, Yaliang Li, Bolin Ding, Jingren Zhou
The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications.
1 code implementation • 11 Apr 2022 • Yuexiang Xie, Zhen Wang, Dawei Gao, Daoyuan Chen, Liuyi Yao, Weirui Kuang, Yaliang Li, Bolin Ding, Jingren Zhou
Although remarkable progress has been made by existing federated learning (FL) platforms to provide infrastructures for development, these platforms may not well tackle the challenges brought by various types of heterogeneity, including the heterogeneity in participants' local data, resources, behaviors and learning goals.
no code implementations • 1 Apr 2022 • Ziqian Chen, Fei Sun, Yifan Tang, Haokun Chen, Jinyang Gao, Bolin Ding
Then we study users' privacy decision making under different data disclosure mechanisms and recommendation models, and how their data disclosure decisions affect the recommender system's performance.
1 code implementation • 6 Feb 2022 • Renzhi Wu, Bolin Ding, Xu Chu, Zhewei Wei, Xiening Dai, Tao Guan, Jingren Zhou
We derive conditions of the learning framework under which the learned model is workload agnostic, in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as, e. g., user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations for unseen tables and workloads.
1 code implementation • 18 Jan 2022 • Chong Chen, Fei Sun, Min Zhang, Bolin Ding
From the perspective of utility, if a system's utility is damaged by some bad data, the system needs to forget these data to regain utility.
no code implementations • 29 Dec 2021 • Andreas Pfadler, Rong Zhu, Wei Chen, Botong Huang, Tianjing Zeng, Bolin Ding, Jingren Zhou
Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers.
1 code implementation • 27 Dec 2021 • Yang Deng, Yaliang Li, Wenxuan Zhang, Bolin Ding, Wai Lam
Recently, Product Question Answering (PQA) on E-Commerce platforms has attracted increasing attention as it can act as an intelligent online shopping assistant and improve the customer shopping experience.
no code implementations • 7 Dec 2021 • Rong Zhu, Tianjing Zeng, Andreas Pfadler, Wei Chen, Bolin Ding, Jingren Zhou
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS.
no code implementations • 29 Sep 2021 • Liuyi Yao, Yaliang Li, Bolin Ding, Jingren Zhou, Jinduo Liu, Mengdi Huai, Jing Gao
To tackle these challenges, we propose a novel casual graph based fair prediction framework, which integrates graph structure learning into fair prediction to ensure that unfair pathways are excluded in the causal graph.
no code implementations • 29 Sep 2021 • Weirui Kuang, Zhen Wang, Yaliang Li, Zhewei Wei, Bolin Ding
We get rid of these obstacles by exploiting the complementary natures of GNN and Transformer, and trade the fine-grained long-range information for the efficiency of Transformer.
no code implementations • ICLR 2022 • Yuexiang Xie, Zhen Wang, Yaliang Li, Ce Zhang, Jingren Zhou, Bolin Ding
However, our further studies uncover that the design of the loss function of Flooding can lead to a discrepancy between its objective and implementation, and cause the instability issue.
no code implementations • 29 Sep 2021 • Daoyuan Chen, Wuchao Li, Yaliang Li, Bolin Ding, Kai Zeng, Defu Lian, Jingren Zhou
We theoretically analyze prediction error bounds that link $\epsilon$ with data characteristics for an illustrative learned index method.
1 code implementation • Findings (EMNLP) 2021 • Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding
However, existing metrics either neglect the intrinsic cause of the factual inconsistency or rely on auxiliary tasks, leading to an unsatisfied correlation with human judgments or increasing the inconvenience of usage in practice.
3 code implementations • 19 Jul 2021 • Yang Li, Yu Shen, Wentao Zhang, Jiawei Jiang, Bolin Ding, Yaliang Li, Jingren Zhou, Zhi Yang, Wentao Wu, Ce Zhang, Bin Cui
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, algorithm/model selection, and hyper-parameter tuning.
no code implementations • 28 May 2021 • Xu Xie, Zhaoyang Liu, Shiwen Wu, Fei Sun, Cihang Liu, Jiawei Chen, Jinyang Gao, Bin Cui, Bolin Ding
It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations.
no code implementations • 20 May 2021 • Yang Deng, Yaliang Li, Fei Sun, Bolin Ding, Wai Lam
However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure.
no code implementations • 5 Mar 2021 • Bolin Ding, Yiding Feng, Chien-Ju Ho, Wei Tang
We study a natural competitive-information-design variant for the Pandora's Box problem (Weitzman 1979), where each box is associated with a strategic information sender who can design what information about the box's prize value to be revealed to the agent when the agent inspects the box.
Computer Science and Game Theory
no code implementations • 9 Jan 2021 • Shuyuan Yan, Bolin Ding, Wei Guo, Jingren Zhou, Zhewei Wei, Xiaowei Jiang, Sheng Xu
Our scalable real-time forecasting system FlashP (Flash Prediction) is built based on this idea, with two major challenges to be resolved in this paper: first, we need to figure out how approximate aggregations affect the fitting of forecasting models, and forecasting results; and second, accordingly, what sampling algorithms we should use to obtain these approximate aggregations and how large the samples are.
no code implementations • 4 Jan 2021 • Yaliang Li, Daoyuan Chen, Bolin Ding, Kai Zeng, Jingren Zhou
In this paper, we propose a formal machine learning based framework to quantify the index learning objective, and study two general and pluggable techniques to enhance the learning efficiency and learning effectiveness for learned indexes.
no code implementations • 1 Jan 2021 • Haokun Chen, Zhaoyang Liu, Chen Xu, Ziqian Chen, Jinyang Gao, Bolin Ding
In this paper, we propose a novel recommendation framework which effectively utilizes the information of user uncertainty over different item dimensions and explicitly takes into consideration the impact of display policy on user in order to achieve maximal expected posterior utility for the platform.
no code implementations • NeurIPS 2020 • Zhiqiang Tao, Yaliang Li, Bolin Ding, Ce Zhang, Jingren Zhou, Yun Fu
Computing the gradient of model hyperparameters, i. e., hypergradient, enables a promising and natural way to solve the hyperparameter optimization task.
1 code implementation • NeurIPS 2020 • Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, Ji-Rong Wen
Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1. 8 billion edges in less than half an hour on a single machine.
1 code implementation • 27 Oct 2020 • Xu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu, Jinyang Gao, Bolin Ding, Bin Cui
Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions.
no code implementations • 29 Jul 2020 • Yuexiang Xie, Zhen Wang, Yaliang Li, Bolin Ding, Nezihe Merve Gürel, Ce Zhang, Minlie Huang, Wei. Lin, Jingren Zhou
Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.
4 code implementations • ICML 2020 • Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li
We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}.
2 code implementations • 21 May 2020 • Ruiyang Ren, Zhao-Yang Liu, Yaliang Li, Wayne Xin Zhao, Hui Wang, Bolin Ding, Ji-Rong Wen
Recently, deep learning has made significant progress in the task of sequential recommendation.
no code implementations • 7 Apr 2020 • Hengtong Zhang, Yaliang Li, Bolin Ding, Jing Gao
In real-world recommendation systems, the cost of retraining recommendation models is high, and the interaction frequency between users and a recommendation system is restricted. Given these real-world restrictions, we propose to let the agent interact with a recommender simulator instead of the target recommendation system and leverage the transferability of the generated adversarial samples to poison the target system.
1 code implementation • 13 Jan 2020 • Daoyuan Chen, Yaliang Li, Minghui Qiu, Zhen Wang, Bofang Li, Bolin Ding, Hongbo Deng, Jun Huang, Wei. Lin, Jingren Zhou
Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.
1 code implementation • ICLR 2020 • Huaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, Zhenhui Li
In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones.
1 code implementation • 30 Aug 2019 • Tianhao Wang, Bolin Ding, Min Xu, Zhicong Huang, Cheng Hong, Jingren Zhou, Ninghui Li, Somesh Jha
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator.
no code implementations • 1 Mar 2019 • Cedric Renggli, Bojan Karlaš, Bolin Ding, Feng Liu, Kevin Schawinski, Wentao Wu, Ce Zhang
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development.
no code implementations • 8 Nov 2018 • Silu Huang, Chi Wang, Bolin Ding, Surajit Chaudhuri
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters.
no code implementations • 10 Oct 2018 • Yaliang Li, Houping Xiao, Zhan Qin, Chenglin Miao, Lu Su, Jing Gao, Kui Ren, Bolin Ding
To better utilize sensory data, the problem of truth discovery, whose goal is to estimate user quality and infer reliable aggregated results through quality-aware data aggregation, has emerged as a hot topic.
no code implementations • NeurIPS 2017 • Bolin Ding, Janardhan Kulkarni, Sergey Yekhanin
In particular, existing LDP algorithms are not suitable for repeated collection of counter data such as daily app usage statistics.
no code implementations • 16 Apr 2017 • Shaoshan Liu, Bolin Ding, Jie Tang, Dawei Sun, Zhe Zhang, Grace Tsai, Jean-Luc Gaudiot
The rise of robotic applications has led to the generation of a huge volume of unstructured data, whereas the current cloud infrastructure was designed to process limited amounts of structured data.