no code implementations • 28 May 2024 • Yuying Duan, Yijun Tian, Nitesh Chawla, Michael Lemmon
Federated Learning (FL) is a distributed machine learning framework in which a set of local communities collaboratively learn a shared global model while retaining all training data locally within each community.
1 code implementation • 16 May 2024 • Lirong Wu, Yijun Tian, Haitao Lin, Yufei Huang, Siyuan Li, Nitesh V Chawla, Stan Z. Li
Protein-protein bindings play a key role in a variety of fundamental biological processes, and thus predicting the effects of amino acid mutations on protein-protein binding is crucial.
1 code implementation • 22 Feb 2024 • Lirong Wu, Yijun Tian, Yufei Huang, Siyuan Li, Haitao Lin, Nitesh V Chawla, Stan Z. Li
In addition, microenvironments defined in previous work are largely based on experimentally assayed physicochemical properties, for which the "vocabulary" is usually extremely small.
no code implementations • 15 Feb 2024 • Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, Meng Jiang
To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts.
no code implementations • 15 Feb 2024 • Zheyuan Liu, Xiaoxin He, Yijun Tian, Nitesh V. Chawla
Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks.
no code implementations • 12 Feb 2024 • Yijun Tian, Chuxu Zhang, Ziyi Kou, Zheyuan Liu, Xiangliang Zhang, Nitesh V. Chawla
In light of this, we propose UGMAE, a unified framework for graph masked autoencoders to address these issues from the perspectives of adaptivity, integrity, complementarity, and consistency.
1 code implementation • 12 Feb 2024 • Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann Lecun, Xavier Bresson, Bryan Hooi
Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface.
no code implementations • 7 Feb 2024 • Yijun Tian, Yikun Han, Xiusi Chen, Wei Wang, Nitesh V. Chawla
To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small student LLM from multiple large teacher LLMs.
no code implementations • 6 Feb 2024 • Zhaoxuan Tan, Qingkai Zeng, Yijun Tian, Zheyuan Liu, Bing Yin, Meng Jiang
OPPU integrates parametric user knowledge in the personal PEFT parameters with the non-parametric knowledge acquired through retrieval and profile.
1 code implementation • 23 Jan 2024 • Lincan Li, Wei Shao, Wei Dong, Yijun Tian, Qiming Zhang, Kaixiang Yang, Wenjie Zhang
There has been a huge bottleneck regarding the upper bound of autonomous driving algorithm performance, a consensus from academia and industry believes that the key to surmount the bottleneck lies in data-centric autonomous driving technology.
1 code implementation • 28 Oct 2023 • Zheyuan Liu, Guangyao Dou, Yijun Tian, Chunhui Zhang, Eli Chien, Ziwei Zhu
Exploring the full spectrum of trade-offs between privacy, model utility, and runtime efficiency is critical for practical unlearning scenarios.
1 code implementation • 27 Sep 2023 • Yijun Tian, Huan Song, Zichen Wang, Haozhu Wang, Ziqing Hu, Fang Wang, Nitesh V. Chawla, Panpan Xu
While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost.
1 code implementation • 9 Apr 2023 • Yihong Ma, Yijun Tian, Nuno Moniz, Nitesh V. Chawla
Concerning the latter, we critically analyze recent work in CILG and discuss urgent lines of inquiry within the topic.
no code implementations • 1 Feb 2023 • Yijun Tian, Shichao Pei, Xiangliang Zhang, Chuxu Zhang, Nitesh V. Chawla
Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, knowledge distillation on graphs (KDG) has been introduced to build a smaller yet effective model and exploit more knowledge from data, leading to model compression and performance improvement.
1 code implementation • 29 Nov 2022 • Kaiwen Dong, Yijun Tian, Zhichun Guo, Yang Yang, Nitesh V. Chawla
In this paper, we first identify the dataset shift problem in the link prediction task and provide theoretical analyses on how existing link prediction methods are vulnerable to it.
no code implementations • 12 Oct 2022 • Zhichun Guo, Chunhui Zhang, Yujie Fan, Yijun Tian, Chuxu Zhang, Nitesh Chawla
In this paper, we propose a novel adaptive KD framework, called BGNN, which sequentially transfers knowledge from multiple GNNs into a student GNN.
no code implementations • 1 Oct 2022 • Chunhui Zhang, Chao Huang, Yijun Tian, Qianlong Wen, Zhongyu Ouyang, Youhuan Li, Yanfang Ye, Chuxu Zhang
The effectiveness is further guaranteed and proved by the gradients' distance between the subset and the full set; (ii) empirically, we discover that during the learning process of a GNN, some samples in the training dataset are informative for providing gradients to update model parameters.
1 code implementation • 22 Aug 2022 • Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, Nitesh V. Chawla
Existing methods attempt to address this scalability issue by training multi-layer perceptrons (MLPs) exclusively on node content features using labels derived from trained GNNs.
1 code implementation • 21 Aug 2022 • Yijun Tian, Kaiwen Dong, Chunhui Zhang, Chuxu Zhang, Nitesh V. Chawla
In light of this, we study the problem of generative SSL on heterogeneous graphs and propose HGMAE, a novel heterogeneous graph masked autoencoder model to address these challenges.
1 code implementation • 8 Jul 2022 • Zhichun Guo, Kehan Guo, Bozhao Nan, Yijun Tian, Roshni G. Iyer, Yihong Ma, Olaf Wiest, Xiangliang Zhang, Wei Wang, Chuxu Zhang, Nitesh V. Chawla
Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning.
no code implementations • 24 May 2022 • Yijun Tian, Chuxu Zhang, Zhichun Guo, Chao Huang, Ronald Metoyer, Nitesh V. Chawla
We then propose RecipeRec, a novel heterogeneous graph learning model for recipe recommendation.
1 code implementation • 24 May 2022 • Yijun Tian, Chuxu Zhang, Zhichun Guo, Yihong Ma, Ronald Metoyer, Nitesh V. Chawla
Learning effective recipe representations is essential in food studies.
no code implementations • 27 Jan 2019 • Yijun Tian
Determining the localization of specific protein in human cells is important for understanding cellular functions and biological processes of underlying diseases.