205 research outputs found
Recommended from our members
Towards Resource-Efficient Trustworthy Distributed Learning
No full textFederated learning (FL) is a collaborative training framework, where multiple edge-devices (users) jointly train a global model, without sharing their private data. Instead, users share the local gradients with a central server after training with their on-device dataset. Several major challenges limit the deployment of conventional FL protocols in real-world large-scale networks. For example, mobile users may drop out from the protocol due to having limited communication and computation resources. Moreover, a single global model may not be optimal for users with heterogeneous data distributions. Lastly, user data can be retrieved even from the shared local gradients through gradient inversion attacks.
Clustered FL is a recent distributed learning mechanism to tackle data heterogeneity in FL, which allows training of multiple global models concurrently, each designated for a cluster of users, i.e., users with similar data distributions. To reduce communication latency in FL, a notable approach is over-the-air aggregation, where users share the same spectrum for sending gradients, enabling gradient aggregation directly over the wireless medium. Gradient sparsification is another widely adopted technique to alleviate communication cost, where each user sends only a small fraction of the entire gradient. For resource-efficient training of large models, a popular approach is submodel learning, which allows users to train a portion of the global model based on their available computing resources and bandwidth. With the prevalence of large foundation models in practical applications, parameter-efficient fine-tuning has recently gained attention, where users only train a few lightweight modules while keeping the pretrained model frozen, significantly reducing resource consumption.
The dissertation addresses several key challenges associated with trustworthy deployment of FL in resource-limited settings. Firstly, we propose an over-the-air aggregation mechanism for clustered FL, which uses the wireless medium to align the local gradients from the same cluster during aggregation, enabling the server to later correctly decode the gradient aggregate for each cluster. The underlying motivation is to tackle data heterogeneity and communication bottleneck simultaneously in large-scale FL settings. Next, we discover that user privacy can be breached when conventional secure aggregation (SA) protocols are naively applied to clustered FL or resource-aware FL protocols. This is attributed to the server's access to auxiliary information like cluster identity (in clustered FL), selected gradient coordinates (in gradient sparsification) or selected submodel indices (in submodel learning) of the user. To prevent associated privacy threats, we propose novel SA protocols, which ensure the information-theoretic privacy of both the auxiliary information and local gradients. Finally, we investigate the privacy risks associated with parameter-efficient fine-tuning, which has been largely underexplored. Accordingly, we identify a novel gradient inversion attack arising from a maliciously crafted pretrained model and fine-tuning modules, which demonstrates high-fidelity data recovery from the shared fine-tuning gradients
Lossy coding of correlated sources over a multiple access channel: necessary conditions and separation results
No full textLossy coding of correlated sources over a multiple access channel (MAC) is studied. First, a joint source-channel coding scheme is presented when the decoder has correlated side information. Next, the optimality of separate source and channel coding, that emerges from the availability of a common observation at the encoders, or side information at the encoders and the decoder, is investigated. It is shown that separation is optimal when the encoders have access to a common observation whose lossless recovery is required at the decoder, and the two sources are independent conditioned on this common observation. Optimality of separation is also proved when the encoder and the decoder have access to shared side information conditioned on which the two sources are independent. These separation results obtained in the presence of side information are then utilized to provide a set of necessary conditions for the transmission of correlated sources over a MAC without side information. Finally, by specializing the obtained necessary conditions to the transmission of binary and Gaussian sources over a MAC, it is shown that they can potentially be tighter than the existing results in the literature, providing a novel converse for this fundamental problem
On the necessary conditions for transmitting correlated sources over a multiple access channel
No full textWe study the lossy communication of correlated
sources over a multiple access channel (MAC). In particular, we
provide a new set of necessary conditions for the achievability of
a distortion pair over a given channel. The necessary conditions
are then specialized to the case of bivariate Gaussian sources and
doubly symmetric binary sources over a Gaussian multiple access
channel. Our results indicate that the new necessary conditions
provide the tightest conditions to date in certain cases
EVALUATION OF ANTIOXIDANT, RADICAL-SCAVENGING AND ACETYLCHOLINESTERASE INHIBITORY ACTIVITIES OF VARIOUS CULINARY HERBS CULTIVATED IN SOUTHERN TURKEY
No full textThe purpose of this study was to determine the antioxidant, radical-scavenging, and acetylcholinesterase inhibitory capabilities of water and methanol extracts of Rhus coriariaL., Ocimum basilicumL., Rosmarinus officinalisL., Salvia officinalisL. and Thymbra spicataL., which are grown in the Hatay province of Turkey. Total antioxidant activities were evaluated using 2,2-diphenyl-1-picrylhydrazyl (22-782.6g/mL EC50),OH scavenging (3.93-33.43g/mL EC50), ferric (0.143-3.083mmol trolox equivalent (TE)/g), and cupric-reducing antioxidant power (0.143-3.083mmol TE/g) assays. The phenolic composition of the methanolic extract of R.coriaria leaves was also investigated, and the active compound was identified as 4-O-methylgallic acid. The highest IC50 value of acetylcholinesterase inhibitory activity (1.170.04mg/mL) was observed in R.coriaria leaves. Principal component analysis showed that R.coriaria leaves possessed greater antioxidant and anti-acetylcholinesterase potential as compared with the other evaluated plants. Practical ApplicationsAntioxidants are widely used in the food industry to prevent the formation of toxic oxidation products and prolong shelf life. Because of increasing concern among consumers about the use of synthetic antioxidants, there has been a great interest in the identification and use of natural antioxidants. The present study reveals that Rhus coriaria leaves, which are not commonly used in Mediterranean cuisine, are a promising source of natural antioxidants and could be considered as a potential source of anti-acetylcholinesterase agents and food preservatives. Both the antioxidant and anti-acetylcholinesterase effects of R.coriaria leaves may be beneficial in the treatment of Alzheimer's disease
Unveiling the actual progress of Digital Building Permit: Getting awareness through a critical state of the art review
No full textGrowing interest is awarded to the digitalization of the building permitting use case and many works are developed about the topic. However, the subject is very complex and many aspects are usually tackled separately, making it very hard for traditional literature reviews to grasp the actual progress in the overall topic. This paper unveils the detailed state of the art in Digital Building Permitting (DBP) by critically analysing the literature by means of a set of coding tags (research progress, implementation, affected DBP workflow steps, ambitions addressed) assigned by a multidisciplinary team. The executed research shows that the mainly addressed aspects of the digitalization of building permit process are the technologies to check the compliance of design proposals against regulations, followed by the digitalization of regulations. Improvable aspects identified in the entire building permit system are instead e.g. the involvement of officers, scalability of solutions and interoperability of data, intended both as data validation and as integration of geospatial data with building models.Urban Data Scienc
- …
