107 citations · 380 across the 45 of their papers we have counts for
46 papers
Data-Topology Compatibility Enables Personalization in Decentralized Learning
Veronica Xu, Lingfei Wang, Chenlei Leng +1
Decentralized learning must balance collaboration with personalization across heterogeneous agents. This paper studies when cooperation can support statistically coherent groups of…
Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
Yuzhu Chen, Tian Qin, Xinmei Tian +2
Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide domains. However, the understanding to the…
DICE: Data Influence Cascade in Decentralized Learning
Tongtian Zhu, Wenhao Li, Can Wang +1
Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through pee…
Lie Symmetry Net: Preserving Conservation Laws in Modelling Financial Market Dynamics via Differential Equations
Xuelian Jiang, Tongtian Zhu, Yingxiang Xu +3
This paper employs a novel Lie symmetries-based framework to model the intrinsic symmetries within financial market. Specifically, we introduce Lie symmetry net (LSN), which charac…
Inverse learning of black-box aggregator for robust Nash equilibrium
Guanpu Chen, Gehui Xu, Fengxiang He +3
In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an…
Boosting Fair Classifier Generalization through Adaptive Priority Reweighing
Zhihao Hu, Yiran Xu, Mengnan Du +3
With the increasing penetration of machine learning applications in critical decision-making areas, calls for algorithmic fairness are more prominent. Although there have been vari…
Heterogeneous Multi-Task Gaussian Cox Processes
Feng Zhou, Quyu Kong, Zhijie Deng +3
This paper presents a novel extension of multi-task Gaussian Cox processes for modeling multiple heterogeneous correlated tasks jointly, e.g., classification and regression, via mu…
-Equivariant Vision Transformer
Renjun Xu, Kaifan Yang, Ke Liu +1
Vision Transformer (ViT) has achieved remarkable performance in computer vision. However, positional encoding in ViT makes it substantially difficult to learn the intrinsic equivar…
Human-imperceptible, Machine-recognizable Images
Fusheng Hao, Fengxiang He, Yikai Wang +4
Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI…
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
Tongtian Zhu, Fengxiang He, Kaixuan Chen +2
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server. However, existing theorie…
Improving Heterogeneous Model Reuse by Density Estimation
Anke Tang, Yong Luo, Han Hu +5
This paper studies multiparty learning, aiming to learn a model using the private data of different participants. Model reuse is a promising solution for multiparty learning, assum…
Learning to Generalize Provably in Learning to Optimize
Junjie Yang, Tianlong Chen, Mingkang Zhu +4
Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizers by data-driven approaches. However, current L2O methods often suffer from poor…
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Chao Xue, Wei Liu, Shuai Xie +25
Automated machine learning (AutoML) seeks to build ML models with minimal human effort. While considerable research has been conducted in the area of AutoML in general, aiming to t…
Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms
Guanpu Chen, Gehui Xu, Fengxiang He +3
Wide machine learning tasks can be formulated as non-convex multi-player games, where Nash equilibrium (NE) is an acceptable solution to all players, since no one can benefit from…
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
Kaiwen Yang, Yanchao Sun, Jiahao Su +5
Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on auto…
Benefits of Permutation-Equivariance in Auction Mechanisms
Tian Qin, Fengxiang He, Dingfeng Shi +2
Designing an incentive-compatible auction mechanism that maximizes the auctioneer's revenue while minimizes the bidders' ex-post regret is an important yet intricate problem in eco…
Bridged Transformer for Vision and Point Cloud 3D Object Detection
Yikai Wang, TengQi Ye, Lele Cao +4
3D object detection is a crucial research topic in computer vision, which usually uses 3D point clouds as input in conventional setups. Recently, there is a trend of leveraging mul…
When to Update Your Model: Constrained Model-based Reinforcement Learning
Tianying Ji, Yu Luo, Fuchun Sun +3
Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization a…
InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference
Mu Yuan, Lan Zhang, Fengxiang He +4
Mobile-centric AI applications have high requirements for resource-efficiency of model inference. Input filtering is a promising approach to eliminate the redundancy so as to reduc…
Super-model ecosystem: A domain-adaptation perspective
Fengxiang He, Dacheng Tao
This paper attempts to establish the theoretical foundation for the emerging super-model paradigm via domain adaptation, where one first trains a very large-scale model, {\it i.e.}…
Shortcut Learning of Large Language Models in Natural Language Understanding
Mengnan Du, Fengxiang He, Na Zou +2
Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and arti…
Topology-aware Generalization of Decentralized SGD
Tongtian Zhu, Fengxiang He, Lan Zhang +3
This paper studies the algorithmic stability and generalizability of decentralized stochastic gradient descent (D-SGD). We prove that the consensus model learned by D-SGD is $\math…
Understanding Deep Learning via Decision Boundary
Shiye Lei, Fengxiang He, Yancheng Yuan +1
This paper discovers that the neural network with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and -data…
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
Rong Dai, Li Shen, Fengxiang He +2
Personalized federated learning is proposed to handle the data heterogeneity problem amongst clients by learning dedicated tailored local models for each user. However, existing wo…