Search Results for author:
Found 26 papers, 4 papers with code
Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
Our optimization methodology aims to select the best combination of sampled nodes and data offloading configuration to maximize FedL training accuracy while minimizing data processing and D2D communication resource consumption subject to realistic constraints on the network topology and device capabilities.
P2O-Calib: Camera-LiDAR Calibration Using Point-Pair Spatial Occlusion Relationship
Based on the extracted 2D-3D point pairs, we further propose an occlusion-guided point-matching method that improves the calibration accuracy and reduces computation costs.
Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
With extensive experimentation and human evaluation on a range of model configurations (LLM, VQA, and T2I), we empirically demonstrate that DSG addresses the challenges noted above.
Mitigating Evasion Attacks in Federated Learning-Based Signal Classifiers
In this work, we first reveal the susceptibility of FL-based signal classifiers to model poisoning attacks, which compromise the training process despite not observing data transmissions.
Multi-Source to Multi-Target Decentralized Federated Domain Adaptation
Our methodology, Source-Target Determination and Link Formation (ST-LF), optimizes both (i) classification of devices into sources and targets and (ii) source-target link formation, in a manner that considers the trade-off between ML model accuracy and communication energy efficiency.
Towards Cooperative Federated Learning over Heterogeneous Edge/Fog Networks
Federated learning (FL) has been promoted as a popular technique for training machine learning (ML) models over edge/fog networks.
Scaling Robot Learning with Semantically Imagined Experience
Specifically, we make use of the state of the art text-to-image diffusion models and perform aggressive data augmentation on top of our existing robotic manipulation datasets via inpainting various unseen objects for manipulation, backgrounds, and distractors with text guidance.
How Potent are Evasion Attacks for Poisoning Federated Learning-Based Signal Classifiers?
In this work, we reveal the susceptibility of FL-based signal classifiers to model poisoning attacks, which compromise the training process despite not observing data transmissions.
Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting
Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.
A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions.
Ranked #1 on
Vision and Language Navigation
on RxR
(using extra training data)
Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks
PSL considers the realistic scenario where global aggregations are conducted with idle times in-between them for resource efficiency improvements, and incorporates data dispersion and model dispersion with local model condensation into FedL.
Less is More: Generating Grounded Navigation Instructions from Landmarks
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes.
threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learning
Recent studies propose leveraging the rich contextual information in data provenance to detect threats in a host.
DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
Experimental results show that DeepAID can provide high-quality interpretations for unsupervised DL models while meeting the special requirements of security domains.
UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach
The presence of time-varying data heterogeneity and computational resource inadequacy among device clusters motivate four key parts of our methodology: (i) stratified UAV swarms of leader, worker, and coordinator UAVs, (ii) hierarchical nested personalized federated learning (HN-PFL), a distributed ML framework for personalized model training across the worker-leader-core network hierarchy, (iii) cooperative UAV resource pooling to address computational inadequacy of devices by conducting model training among the UAV swarms, and (iv) model/concept drift to model time-varying data distributions.
On the Evaluation of Vision-and-Language Navigation Instructions
Vision-and-Language Navigation wayfinding agents can be enhanced by exploiting automatically generated navigation instructions.
Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server.
GenAD: General Representations of Multivariate Time Series for Anomaly Detection
However, due to complex correlations and various temporal patterns of large-scale multivariate time series, a general unsupervised anomaly detection model with higher F1-score and Timeliness remains a challenging task.
Narrative Interpolation for Generating and Understanding Stories
We propose a method for controlled narrative/story generation where we are able to guide the model to produce coherent narratives with user-specified target endings by interpolation: for example, we are told that Jim went hiking and at the end Jim needed to be rescued, and we want the model to incrementally generate steps along the way.
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
Query-Focused Scenario Construction
The news coverage of events often contains not one but multiple incompatible accounts of what happened.
A task in a suit and a tie: paraphrase generation with semantic augmentation
Paraphrasing is rooted in semantics.
Picking Apart Story Salads
During natural disasters and conflicts, information about what happened is often confusing, messy, and distributed across many sources.
Modeling Semantic Plausibility by Injecting World Knowledge
Distributional data tells us that a man can swallow candy, but not that a man can swallow a paintball, since this is never attested.
Leveraging Discourse Information Effectively for Authorship Attribution
We explore techniques to maximize the effectiveness of discourse information in the task of authorship attribution.
Distributional Modeling on a Diet: One-shot Word Learning from Text Only
We test whether distributional models can do one-shot learning of definitional properties from text only.
