Search Results for author:
Found 19 papers, 6 papers with code
FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations
In edge computing, users' service profiles must be migrated in response to user mobility.
pFedDef: Defending Grey-Box Attacks for Personalized Federated Learning
We are the first to characterize the transferability of such internal evasion attacks for different learning methods and analyze the trade-off between model accuracy and robustness depending on the degree of personalization and similarities in client data.
Hierarchical Conversational Preference Elicitation with Bandit Feedback
To achieve this, the recommender system conducts conversations with users, asking their preferences for different items or item categories.
Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications.
Faithful Explanations for Deep Graph Models
Second, our analytical and empirical results demonstrate that feature attribution methods cannot capture the nonlinear effect of edge features, while existing subgraph explanation methods are not faithful.
FedGCN: Convergence and Communication Tradeoffs in Federated Training of Graph Convolutional Networks
We then introduce Federated Graph Convolutional Network (FedGCN), which uses federated learning to train GCN models for semi-supervised node classification on large graphs with optimized convergence rate and communication cost.
FedSoft: Soft Clustered Federated Learning with Proximal Local Updating
Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution.
GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs
These works, however, do not fully address the challenge of flexibly assigning different importance to snapshots of the graph at different times, which depending on the graph dynamics may have more or less predictive power on the labels.
Combinatorial Multi-armed Bandits for Resource Allocation
In doing so, the decision maker should learn the value of the resources allocated for each user from feedback on each user's received reward.
Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks
We characterize the optimal decay rate for each cluster and propose a clustering method that achieves almost exact recovery of the true clusters.
Can we Generalize and Distribute Private Representation Learning?
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
Reconstructing Actions To Explain Deep Reinforcement Learning
Feature attribution has been a foundational building block for explaining the input feature importance in supervised learning with Deep Neural Network (DNNs), but face new challenges when applied to deep Reinforcement Learning (RL). We propose a new approach to explaining deep RL actions by defining a class of \emph{action reconstruction} functions that mimic the behavior of a network in deep RL.
Online Competitive Influence Maximization
In this paper, we introduce a new Online Competitive Influence Maximization (OCIM) problem, where two competing items (e. g., products, news stories) propagate in the same network and influence probabilities on edges are unknown.
Towards Flexible Device Participation in Federated Learning
Traditional federated learning algorithms impose strict requirements on the participation rates of devices, which limit the potential reach of federated learning.
Network-Aware Optimization of Distributed Learning for Fog Computing
Unlike traditional federated learning frameworks, our method enables devices to offload their data processing tasks to each other, with these decisions determined through a convex data transfer optimization problem that trades off costs associated with devices processing, offloading, and discarding data points.
Distributed, Parallel, and Cluster Computing
Machine Learning on Volatile Instances
Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple worker nodes.
Observe Before Play: Multi-armed Bandit with Pre-observations
We consider the stochastic multi-armed bandit (MAB) problem in a setting where a player can pay to pre-observe arm rewards before playing an arm in each round.
MOVI: A Model-Free Approach to Dynamic Fleet Management
Since DQNs scale poorly with a large number of possible dispatches, we streamline our DQN training and suppose that each individual vehicle independently learns its own optimal policy, ensuring scalability at the cost of less coordination between vehicles.
On the Real-time Vehicle Placement Problem
Motivated by ride-sharing platforms' efforts to reduce their riders' wait times for a vehicle, this paper introduces a novel problem of placing vehicles to fulfill real-time pickup requests in a spatially and temporally changing environment.
