Search Results for author:
Found 47 papers, 20 papers with code
Human-imperceptible, Machine-recognizable Images
Massive human-related data is collected to train neural networks for computer vision tasks.
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server.
Improving Heterogeneous Model Reuse by Density Estimation
This paper studies multiparty learning, aiming to learn a model using the private data of different participants.
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
Learning to Generalize Provably in Learning to Optimize
While the optimizer generalization has been recently studied, the optimizee generalization (or learning to generalize) has not been rigorously studied in the L2O context, which is the aim of this paper.
Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms
This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping.
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
In experiments, we show that our method consistently brings non-trivial improvements to the three aforementioned learning tasks from both efficiency and final performance, either or not combined with strong pre-defined augmentations, e. g., on medical images when domain knowledge is unavailable and the existing augmentation techniques perform poorly.
When to Update Your Model: Constrained Model-based Reinforcement Learning
Our follow-up derived bounds reveal the relationship between model shifts and performance improvement.
Model-based Reinforcement Learning
reinforcement-learning
+1
Benefits of Permutation-Equivariance in Auction Mechanisms
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 economics.
Bridged Transformer for Vision and Point Cloud 3D Object Detection
Recently, there is a trend of leveraging multiple sources of input data, such as complementing the 3D point cloud with 2D images that often have richer color and fewer noises.
InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference
Previous efforts have tailored effective solutions for many applications, but left two essential questions unanswered: (1) theoretical filterability of an inference workload to guide the application of input filtering techniques, thereby avoiding the trial-and-error cost for resource-constrained mobile applications; (2) robust discriminability of feature embedding to allow input filtering to be widely effective for diverse inference tasks and input content.
Super-model ecosystem: A domain-adaptation perspective
We model the super-model paradigm as a two-stage diffusion process: (1) in the pre-training stage, the model parameter diffuses from random initials and converges to a steady distribution; and (2) in the fine-tuning stage, the model parameter is transported to another steady distribution.
Shortcut Learning of Large Language Models in Natural Language Understanding
We first introduce the concepts of shortcut learning of language models.
Topology-aware Generalization of Decentralized SGD
Our theory indicates that the generalizability of D-SGD is positively correlated with the spectral gap, and can explain why consensus control in initial training phase can ensure better generalization.
Understanding deep learning via decision boundary
From the theoretical view, two lower bounds based on algorithm DB variability are proposed and do not explicitly depend on the sample size.
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
In this work, we propose a novel personalized federated learning framework in a decentralized (peer-to-peer) communication protocol named Dis-PFL, which employs personalized sparse masks to customize sparse local models on the edge.
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
The tangent transfer creates initial augmented samples for improving corruption robustness.
Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
To address this concern, methods are proposed to make data unlearnable for deep learning models by adding a type of error-minimizing noise.
Knowledge Removal in Sampling-based Bayesian Inference
In this paper, we propose the first machine unlearning algorithm for MCMC.
Exploring High-Order Structure for Robust Graph Structure Learning
In this paper, we analyze the adversarial attack on graphs from the perspective of feature smoothness which further contributes to an efficient new adversarial defensive algorithm for GNNs.
Achieving Personalized Federated Learning with Sparse Local Models
To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user.
Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i. e., the model generates the layout and then synthesizes images from the layout and captions.
Siamese Network with Interactive Transformer for Video Object Segmentation
Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied in recent years.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #3 on
Scene Text Recognition
on SVTP
(using extra training data)
Self-Ensembling GAN for Cross-Domain Semantic Segmentation
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.
Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks
The bound scales with the spectral complexity, the dominant factor of which is the spectral norm product of weight matrices.
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
For the application of dense image prediction, the validity of CEN is tested by four different scenarios: multimodal fusion, cycle multimodal fusion, multitask learning, and multimodal multitask learning.
Ranked #16 on
Semantic Segmentation
on NYU Depth v2
Theoretical understanding of adversarial reinforcement learning via mean-field optimal control
A new mean-field Pontryagin's maximum principle is proposed for reinforcement learning with implicit terminal constraints.
Decision boundary variability and generalization in neural networks
Two new notions, algorithm DB variability and $(\epsilon, \eta)$-data DB variability, are proposed to measure the decision boundary variability from the algorithm and data perspectives.
Generalizable Learning to Optimize into Wide Valleys
Learning to optimize (L2O) has gained increasing popularity in various optimization tasks, since classical optimizers usually require laborious, problem-specific design and hyperparameter tuning.
Huber Additive Models for Non-stationary Time Series Analysis
Moreover, the error bound for non-stationary time series contains a discrepancy measure for the shifts of the data distributions over time.
Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning
To address this concern, methods are proposed to make data unlearnable for deep learning models by adding a type of error-minimizing noise.
On Heterogeneously Distributed Data, Sparsity Matters
Federated learning (FL) is particularly vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user.
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.
Bayesian Inference Forgetting
This paper proposes a {\it Bayesian inference forgetting} (BIF) framework to realize the right to be forgotten in Bayesian inference.
Neural networks behave as hash encoders: An empirical study
We then define an {\it activation hash phase chart} to represent the space expanded by {model size}, training time, training sample size, and the encoding properties, which is divided into three canonical regions: {\it under-expressive regime}, {\it critically-expressive regime}, and {\it sufficiently-expressive regime}.
Robustness, Privacy, and Generalization of Adversarial Training
This measure can be approximate empirically by an asymptotically consistent empirical estimator, {\it empirical robustified intensity}.
Recent advances in deep learning theory
Deep learning is usually described as an experiment-driven field under continuous criticizes of lacking theoretical foundations.
Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
Thus it motivates us to design a similar mechanism named {\it artificial neural variability} (ANV), which helps artificial neural networks learn some advantages from ``natural'' neural networks.
Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
This paper studies the relationship between generalization and privacy preservation in iterative learning algorithms by two sequential steps.
Understanding Generalization in Recurrent Neural Networks
We first present a new generalization bound for recurrent neural networks based on matrix 1-norm and Fisher-Rao norm.
Piecewise linear activations substantially shape the loss surfaces of neural networks
This result holds for any neural network with arbitrary depth and arbitrary piecewise linear activation functions (excluding linear functions) under most loss functions in practice.
Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
Specifically, we prove a PAC-Bayes generalization bound for neural networks trained by SGD, which has a positive correlation with the ratio of batch size to learning rate.
Fast Spatio-Temporal Residual Network for Video Super-Resolution
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance.
Why ResNet Works? Residuals Generalize
This paper studies the influence of residual connections on the hypothesis complexity of the neural network in terms of the covering number of its hypothesis space.
Instance-Dependent PU Learning by Bayesian Optimal Relabeling
Specifically, by treating the unlabelled data as noisy negative examples, we could automatically label a group positive and negative examples whose labels are identical to the ones assigned by a Bayesian optimal classifier with a consistency guarantee.
