no code implementations • 31 Jan 2024 • Zhitian Xie, Yinger Zhang, Chenyi Zhuang, Qitao Shi, Zhining Liu, Jinjie Gu, Guannan Zhang
However, the gate's routing mechanism also gives rise to narrow vision: the individual MoE's expert fails to use more samples in learning the allocated sub-task, which in turn limits the MoE to further improve its generalization ability.
no code implementations • 15 Dec 2023 • Xingyu Lu, Zhining Liu, Yanchu Guan, Hongxuan Zhang, Chenyi Zhuang, Wenqi Ma, Yize Tan, Jinjie Gu, Guannan Zhang
of a cascade RS, when a user triggers a request, we define two actions that determine the computation: (1) the trained instances of models with different computational complexity; and (2) the number of items to be inferred in the stage.
1 code implementation • 14 Nov 2023 • Hongxuan Zhang, Zhining Liu, Jiaqi Zheng, Chenyi Zhuang, Jinjie Gu, Guihai Chen
In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself.
no code implementations • 6 Oct 2023 • Zhichen Zeng, Boxin Du, Si Zhang, Yinglong Xia, Zhining Liu, Hanghang Tong
To depict high-order relationships across multiple networks, the FGW distance is generalized to the multi-marginal setting, based on which networks can be aligned jointly.
no code implementations • 29 Aug 2023 • Hyunsik Yoo, Zhichen Zeng, Jian Kang, Ruizhong Qiu, David Zhou, Zhining Liu, Fei Wang, Charlie Xu, Eunice Chan, Hanghang Tong
In the ever-evolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences.
no code implementations • 27 Aug 2023 • Zhining Liu, Zhichen Zeng, Ruizhong Qiu, Hyunsik Yoo, David Zhou, Zhe Xu, Yada Zhu, Kommy Weldemariam, Jingrui He, Hanghang Tong
Class imbalance is prevalent in real-world node classification tasks and often biases graph learning models toward majority classes.
1 code implementation • 3 Jun 2023 • Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian
This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods.
no code implementations • 28 Dec 2021 • Xuanying Chen, Zhining Liu, Li Yu, Sen Li, Lihong Gu, Xiaodong Zeng, Yize Tan, Jinjie Gu
This bias deteriorates the performance of the response model and misleads the linear programming process, dramatically degrading the performance of the resulting allocation policy.
1 code implementation • 24 Nov 2021 • Zhining Liu, Pengfei Wei, Zhepei Wei, Boyang Yu, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang
Class-imbalance is a common problem in machine learning practice.
1 code implementation • 24 Nov 2021 • Zhining Liu, Jian Kang, Hanghang Tong, Yi Chang
imbalanced-ensemble, abbreviated as imbens, is an open-source Python toolbox for leveraging the power of ensemble learning to address the class imbalance problem.
2 code implementations • NeurIPS 2020 • Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang
This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.
1 code implementation • 8 Sep 2019 • Zhining Liu, Wei Cao, Zhifeng Gao, Jiang Bian, Hechang Chen, Yi Chang, Tie-Yan Liu
To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers.
no code implementations • IEEE Access 2019 • Zhining Liu, Weiyi Liu, Pin-Yu Chen, Chenyi Zhuang, Chengyun Song
Graph neural networks (GNNs) have recently made remarkable breakthroughs in the paradigm of learning with graph-structured data.
Ranked #39 on
Node Classification
on Citeseer
no code implementations • 17 Apr 2018 • Weiyi Liu, Zhining Liu, Toyotaro Suzumura, Guangmin Hu
Here we propose \emph{SANE}, a scalable attribute-aware network embedding algorithm with locality, to learn the joint representation from topology and attributes.