Search Results for author:
Found 64 papers, 10 papers with code
Why Go Full? Elevating Federated Learning Through Partial Network Updates
In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round.
Learning Submodular Sequencing from Samples
We present an algorithm that, given polynomially many samples drawn from a two-stage uniform distribution, achieves an approximation ratio dependent on the curvature of individual submodular functions.
The Power of Second Chance: Personalized Submodular Maximization with Two Candidates
In this paper, we introduce the problem of personalized submodular maximization with two candidate solutions.
DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations
In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature.
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
In this paper, we propose a new PFL framework called FedPFT to address the mismatch problem while enhancing the quality of the feature extractor.
The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learning
We note that when dealing with clients with similar data distributions, methods such as personalized weight aggregation tend to enforce their models to be close in the parameter space.
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition
Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge.
Submodular Participatory Budgeting
To address this, we extend the existing study by proposing a submodular participatory budgeting problem, assuming that the utility function of each individual is a monotone and submodular function over funded projects.
Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning
Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model. In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towards some certain classes.
Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations.
Point cloud-based registration and image fusion between cardiac SPECT MPI and CTA
Fourthly, we employed ICP, SICP or CPD algorithm to achieve a fine registration for the point clouds (together with the special points of APIGs) of the LV epicardial surfaces (LVERs) in SPECT and CTA images.
Assortment Planning with Sponsored Products
In the rapidly evolving landscape of retail, assortment planning plays a crucial role in determining the success of a business.
Efficient Generalized Low-Rank Tensor Contextual Bandits
In this paper, we aim to build a novel bandits algorithm that is capable of fully harnessing the power of multi-dimensional data and the inherent non-linearity of reward functions to provide high-usable and accountable decision-making services.
Lifting the Veil: Unlocking the Power of Depth in Q-learning
In this paper, we make fundamental contributions to the field of reinforcement learning by answering to the following three questions: Why does deep Q-learning perform so well?
Provable Tensor Completion with Graph Information
For the model, we establish a rigorous mathematical representation of the dynamic graph, based on which we derive a new tensor-oriented graph smoothness regularization.
Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration
The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration.
Data Summarization beyond Monotonicity: Non-monotone Two-Stage Submodular Maximization
The objective of a two-stage submodular maximization problem is to reduce the ground set using provided training functions that are submodular, with the aim of ensuring that optimizing new objective functions over the reduced ground set yields results comparable to those obtained over the original ground set.
Non-monotone Sequential Submodular Maximization
In this paper, we study a fundamental problem in submodular optimization, which is called sequential submodular maximization.
Take Your Pick: Enabling Effective Personalized Federated Learning within Low-dimensional Feature Space
FedPick achieves PFL in the low-dimensional feature space by selecting task-relevant features adaptively for each client from the features generated by the global encoder based on its local data distribution.
Unlocking the Potential of Federated Learning for Deeper Models
Our further investigation shows that the decline is due to the continuous accumulation of dissimilarities among client models during the layer-by-layer back-propagation process, which we refer to as "divergence accumulation."
Beyond Submodularity: A Unified Framework of Randomized Set Selection with Group Fairness Constraints
Our problem involves a global utility function and a set of group utility functions for each group, here a group refers to a group of individuals (e. g., people) sharing the same attributes (e. g., gender).
Achieving Long-term Fairness in Submodular Maximization through Randomization
Unlike previous studies in this area, we allow for randomized solutions, with the objective being to calculate a distribution over feasible sets such that the expected number of items selected from each group is subject to constraints in the form of upper and lower thresholds, ensuring that the representation of each group remains balanced in the long term.
DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models
In this work, we propose a device-cloud collaborative controlled learning framework, called DC-CCL, enabling a cloud-side large vision model that cannot be directly deployed on the mobile device to still benefit from the device-side local samples.
Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes
The novelties of our research are as follows: 1) From a methodological perspective, we present a novel and scalable approach for generating DTRs by combining distributed learning with Q-learning.
Group Fairness in Non-monotone Submodular Maximization
Our goal is to select a set of items that maximizes a non-monotone submodular function, while ensuring that the number of selected items from each group is proportionate to its size, to the extent specified by the decision maker.
One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design
The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with heterogeneous images from a small subset of classes to be recognized.
Worst-Case Adaptive Submodular Cover
We also study a worst-case maximum-coverage problem, a dual problem of the minimum-cost-cover problem, whose goal is to select a group of items to maximize its worst-case utility subject to a budget constraint.
On-Device Model Fine-Tuning with Label Correction in Recommender Systems
To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mobile devices.
Evolution is Still Good: Theoretical Analysis of Evolutionary Algorithms on General Cover Problems
Theoretical studies on evolutionary algorithms have developed vigorously in recent years.
Streaming Adaptive Submodular Maximization
Many sequential decision making problems can be formulated as an adaptive submodular maximization problem.
Partial-Monotone Adaptive Submodular Maximization
We show that a sampling-based policy achieves an approximation ratio of $(m+1)/10$ if the utility function is $m$-adaptive monotone and adaptive submodular.
Group Equality in Adaptive Submodular Maximization
In this paper, we study the classic submodular maximization problem subject to a group equality constraint under both non-adaptive and adaptive settings.
A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images
Conclusion: Our proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV function.
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.
On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems
Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to each individual user's local data distribution.
Constrained Stochastic Submodular Maximization with State-Dependent Costs
Recall that each item has a state-dependent cost, and the inner constraint states that the total \emph{realized} cost of all selected items must not exceed a give budget.
Partial-Adaptive Submodular Maximization
Although this approach can take full advantage of feedback from the past to make informed decisions, it may take a longer time to complete the selection process as compared with the non-adaptive solution where all selections are made in advance before any observations take place.
Submodular Optimization Beyond Nonnegativity: Adaptive Seed Selection in Incentivized Social Advertising
We formulate this problem as a seed selection problem whose objective function is non-monotone and it might take on negative values, making existing results on submodular optimization and influence maximization not applicable to our setting.
Federated Submodel Optimization for Hot and Cold Data Features
We theoretically proved the convergence rate of FedSubAvg by deriving an upper bound under a new metric called the element-wise gradient norm.
Data-Free Evaluation of User Contributions in Federated Learning
We evaluate the performance of PCA and Fed-PCA using the MNIST dataset and a large industrial product recommendation dataset.
Robust Adaptive Submodular Maximization
For the worst-case adaptive submodular maximization problem subject to a $p$-system constraint, we develop an adaptive worst-case greedy policy that achieves a $\frac{1}{p+1}$ approximation ratio against the optimal worst-case utility if the utility function is worst-case submodular.
Beyond Pointwise Submodularity: Non-Monotone Adaptive Submodular Maximization subject to Knapsack and $k$-System Constraints
Our objective is to sequentially select a group of items to maximize the expected utility.
Optimal Sampling Gaps for Adaptive Submodular Maximization
Although the benefit of running machine learning algorithms on the reduced data set is obvious, one major concern is that the performance of the solution obtained from samples might be much worse than that of the optimal solution when using the full data set.
Adaptive Regularized Submodular Maximization
For the case when $g$ is adaptive monotone and adaptive submodular, we develop an effective policy $\pi^l$ such that $g_{avg}(\pi^l) - c_{avg}(\pi^l) \geq (1-\frac{1}{e}-\epsilon)g_{avg}(\pi^o) - c_{avg}(\pi^o)$, using only $O(n\epsilon^{-2}\log \epsilon^{-1})$ value oracle queries.
A Deep Learning-Based Approach to Extracting Periosteal and Endosteal Contours of Proximal Femur in Quantitative CT Images
In this study, we proposed an approach based on deep learning for the automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments.
Toward Understanding the Influence of Individual Clients in Federated Learning
Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server.
Adaptive Submodular Meta-Learning
Our objective is to adaptively select a group of items that achieve the best performance over a set of tasks, where each task is represented as an adaptive submodular function that maps sets of items and their states to a real number.
SelectScale: Mining More Patterns from Images via Selective and Soft Dropout
Instead of randomly dropping units, SelectScale selects the important features in networks and adjusts them during training.
Beyond Pointwise Submodularity: Non-Monotone Adaptive Submodular Maximization in Linear Time
Our first contribution is to show that the adaptive random greedy algorithm achieves a $1/e$ approximation ratio under adaptive submodularity.
Linear-Time Algorithms for Adaptive Submodular Maximization
We start with the well-studied adaptive submodular maximization problem subject to a cardinality constraint.
Adaptive Cascade Submodular Maximization
The input of our problem is a set of items, each item is in a particular state (i. e., the marginal contribution of an item) which is drawn from a known probability distribution.
A Novel Method for ECG Signal Classification via One-Dimensional Convolutional Neural Network
This paper presents an end-to-end ECG signal classification method based on a novel segmentation strategy via 1D Convolutional Neural Networks (CNN) to aid the classification of ECG signals.
A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area.
Distributed Optimization over Block-Cyclic Data
We consider practical data characteristics underlying federated learning, where unbalanced and non-i. i. d.
Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability
In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, where the set of eligible clients may change during the training process.
Assortment Optimization with Repeated Exposures and Product-dependent Patience Cost
After browsing all products in one stage, if the utility of a product exceeds the utility of the outside option, the consumer proceeds to purchase the product and leave the platform.
Online Pricing with Reserve Price Constraint for Personal Data Markets
The analysis and evaluation results reveal that our proposed pricing mechanism incurs low practical regret, online latency, and memory overhead, and also demonstrate that the existence of reserve price can mitigate the cold-start problem in a posted price mechanism, and thus can reduce the cumulative regret.
Secure Federated Submodel Learning
Nevertheless, the "position" of a client's truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning.
Stochastic Submodular Probing with State-Dependent Costs
The only way to know the realized state of an item is to probe that item.
Adaptive Robust Optimization with Nearly Submodular Structure
Then we propose a approximate solution to this problem when all reward functions are submodular.
Cascade Submodular Maximization: Question Selection and Sequencing in Online Personality Quiz
Note that under the our model, the probability of a question being answered depends on the location of that question, as well as the set of other questions placed ahead of that question, this makes our problem fundamentally different from existing studies on submodular optimization.
No Time to Observe: Adaptive Influence Maximization with Partial Feedback
In the full-feedback model, we select one seed at a time and wait until the diffusion completes, before selecting the next seed.
Social and Information Networks
Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies
In particular, we consider the setting of a decision maker over a networked bandits as follows: each time a combinatorial strategy, e. g., a group of arms, is chosen, and the decision maker receives a reward resulting from her strategy and also receives a side bonus resulting from that strategy for each arm's neighbor.
Towards Distribution-Free Multi-Armed Bandits with Combinatorial Strategies
At each decision epoch, we select a strategy, i. e., a subset of RVs, subject to arbitrary constraints on constituent RVs.
