We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three ...
详细信息
A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature. Nevertheless, statistical significance testing (SST) is still not widely used. This endangers true progress, as seeming improve...
详细信息
This paper considers the decentralized (discrete) optimal transport (D-OT) problem. In this setting, a network of agents seeks to design a transportation plan jointly, where the cost function is the sum of privately h...
详细信息
ISBN:
(数字)9798350382655
ISBN:
(纸本)9798350382662
This paper considers the decentralized (discrete) optimal transport (D-OT) problem. In this setting, a network of agents seeks to design a transportation plan jointly, where the cost function is the sum of privately held costs for each agent. We reformulate the D-OT problem as a constraint-coupled optimization problem and propose a single-loop decentralized algorithm with an iteration complexity of
$O(1/\epsilon)$
that matches existing centralized first-order approaches. Moreover, we propose the decentralized equitable optimal transport (DE-OT) problem. In DE-OT, in addition to cooperatively designing a transportation plan that minimizes transportation costs, agents seek to ensure equity in their individual costs. The iteration complexity of the proposed method to solve DE-OT is also
$O(1/\epsilon)$
. This rate improves existing centralized algorithms, where the best iteration complexity obtained is
$O(1/\epsilon^{2})$
.
Quantization of a toy model of a pseudointegrable Hamiltonian impact system is introduced, including EBK quantization conditions, a verification of Weyl’s law, the study of their wavefunctions and a study of their en...
详细信息
An i-packing in a graph G is a set of vertices that are pairwise at distance more than i. A packing colouring of G is a partition X = {X1, X2, ..., Xk} of V (G) such that each colour class Xi is an i-packing. The mini...
详细信息
Integrating transformers with graph representation learning has emerged as a research focal point. However, recent studies showed that positional encoding in Transformers does not capture enough structural information...
Integrating transformers with graph representation learning has emerged as a research focal point. However, recent studies showed that positional encoding in Transformers does not capture enough structural information between nodes. Additionally, existing graph neural network (GNN) models face the oversquashing issue, impeding information retention from distant nodes. To address, we transform graphs into regular structures, such as tokens, to enhance positional understanding and leverage transformer strengths. Inspired by the visual transformer (ViT) model, we propose partitioning graphs into patches and apply GNN models obtain fixed size vectors. Notably, our approach adopts contrastive learning for in-depth graph structure and incorporate more topological information via Ricci curvature to alleviate over-squashing problem by attenuating the effects of negatively curved edges while preserving the original graph structure. Unlike existing graph rewiring methods that directly modify graph structure by adding or removing edges, this approach is potentially more suitable for applications such as molecular learning where structural preservation is important. Our innovative pipeline subsequently introduces the PerformerMixer, a transformer variant with linear complexity, ensuring efficient computation. Evaluations on real-world benchmarks demonstrate our framework’s superior performance, like Peptides-func and achieve 3-WL expressiveness.
Information about human presence in indoor spaces is crucial for building energy optimization. While there has been a considerable amount of research on using neural networks to automatically detect occupancy from CO2...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
Information about human presence in indoor spaces is crucial for building energy optimization. While there has been a considerable amount of research on using neural networks to automatically detect occupancy from CO2 sensors, their application in practice is limited due to the scarcity of labeled training data. In this paper, we propose Coddora, an off-the-shelf deep learning model pretrained on data from randomized room simulations. Coddora enables quick adaptation to real-world rooms, requiring only minimal data collection. Our contribution includes two model variants for application via fine-tuning or zero-shot classifying, as well as the synthetic dataset providing data from simulations with 100,000 room models.
In today's rapidly evolving technological landscape, ensuring the security of systems requires continuous authentication over sessions and comprehensive access management during user interaction with a device. Wit...
详细信息
In the increasingly digitized world, the privacy and security of sensitive data shared via IoT devices are paramount. Traditional privacy-preserving methods like k-anonymity and ldiversity are becoming outdated due to...
详细信息
In the increasingly digitized world, the privacy and security of sensitive data shared via IoT devices are paramount. Traditional privacy-preserving methods like k-anonymity and ldiversity are becoming outdated due to technological advancements. In addition, data owners often worry about misuse and unauthorized access to their personal information. To address this, we propose a secure data-sharing framework that uses local differential privacy (LDP) within a permissioned blockchain, enhanced by federated learning (FL) in a zero-trust environment. To further protect sensitive data shared by IoT devices, we use the Interplanetary File System (IPFS) and cryptographic hash functions to create unique digital fingerprints for files. We mainly evaluate our system based on latency, throughput, privacy accuracy, and transaction efficiency, comparing the performance to a benchmark model. The experimental results show that the proposed system outperforms its counterpart in terms of latency, throughput, and transaction efficiency. The proposed model achieved a lower average latency of 4.0 seconds compared to the benchmark model’s 5.3 seconds. In terms of throughput, the proposed model achieved a higher throughput of 10.53 TPS (transactions per second) compared to the benchmark model’s 8 TPS. Furthermore, the proposed system achieves 85% accuracy, whereas the counterpart achieves only 49%. IEEE
The advent of smart home technologies has opened new avenues for personalized healthcare, energy management, and enhanced convenience. However, variations in resident behavior, sensor types, and home layouts cause dom...
详细信息
ISBN:
(数字)9798331510503
ISBN:
(纸本)9798331510510
The advent of smart home technologies has opened new avenues for personalized healthcare, energy management, and enhanced convenience. However, variations in resident behavior, sensor types, and home layouts cause domain shifts, posing significant challenges to the deployment of machine learning models across diverse smart home environments. This paper describes a new method that uses domain adaptation layers in a transfer learning framework to change domain-specific features on the fly. This makes cross-data set generalization better. We compare the proposed method against Standard Transfer Learning, Domain-Adversarial Neural Networks (DANN), and Correlation Alignment (CORAL) using multiple smart home data sets. Our evaluation demonstrates that the proposed method significantly outperforms these existing approaches in terms of predictive performance, highlighting its effectiveness in addressing domain shifts in smart home environments.
暂无评论