FedLoRA-C by Lokanatha Reddy Gandikota

#IEEE #CVT #STEM #GPS #GNSS #IEEE-USA
Share

Dallas Section - IEEE CVT

Dallas CVT October 2026 Meeting

One-Week Reminder

Dallas IEEE Communications and Vehicular Society member,

Please join us for our October 2026 CVT meeting. 

We will again meet on the University of Texas at Dallas campus in the SPN.1 building.
Our meeting will be from 12:00 PM to 1:00 PM, and lunch will be available starting around 11:30 AM.

Lunch: We continue to provide a lunch option for our meetings.

Prepay via the IEEE website,
IEEE Members $10.00
IEEE Life Members $5.00
Non-IEEE Members $15.00
Fulltime UTD ECE students: $2.00 (The first 5 pre-registered will be free)

Pay in person:
IEEE Members $15.00
IEEE Life Members $10.00
Non-IEEE Members $20.00

October 20 meeting, UT Dallas SPN.1, registration opens at 11:30 AM, talk begins at 12:00 PM

Title:       "FedLoRA-C: Communication-Efficient Federated Fine-Tuning of Large Language Models via Selective Layer Compression"
Speaker:  Lokanatha Reddy Gandikota, Distinguished Engineer at Verizon, Dallas, TX.

 
Date:        October 20, 2026
Location: UTD Synergy Park North Building; 3000 Waterview, Richardson, TX
Directions: NE Corner Synergy Park Blvd and Steward Dr.
Lunch Cost:  see below.

Abstract:

Fine-tuning large language models across distributed institutions — hospitals, law firms, financial organizations — is often blocked by two constraints: sensitive data cannot be centralized, and the communication cost of coordinating model updates becomes prohibitive at scale. This talk presents FedLoRA-C, a communication-efficient framework for federated fine-tuning of LLMs. By combining Low-Rank Adaptation with a novel Selective Layer Compression strategy that identifies and prioritizes the transformer layers most critical to task adaptation, FedLoRA-C reduces per-round communication cost by 67.3% while achieving accuracy within 1.4% of centralized fine-tuning. The talk covers the core method, results across four NLP benchmarks including a healthcare question-answering task, and practical implications for deploying LLM adaptation in privacy-sensitive, bandwidth-constrained settings. The work received the Best Industrial Paper Award at IEEE AIS 2026.

 

Pre-registered and paid via the IEEE website: 
IEEE Members $10.00
IEEE Life Members $5.00
Non-IEEE Members $15.00
UTD ECE students: $2.00

Pay in person and pre-registered but not yet paid:
IEEE Members $15.00
IEEE Life Members $10.00
Non-IEEE Members $20.00

Anyone not pre-registered will be charged the ‘Guest’ rate.

There is No charge for 'No Lunch, just attending the talk'.

Thanks in advance, and all the best.

Divya K.

Anyone without pre-registration for lunch will be asked to wait until all pre-registered guests have had a chance to go through the buffet line. 

Dallas IEEE CVT Board members' emails:

larryjhorner@gmail.com
andrewsilver@ieee.org
jimgunn@ieee.org
shmuel.hovav@gmail.com
eb0549@att.com
divya.khanure@ieee.org
ed.hightower@iotandbeyond.com
dinesh@utdallas.edu


 


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar
  • 3000 Waterview Pkwy
  • Richardson, Texas
  • United States 75080
  • Building: SPN 1
  • Room Number: 2.220
  • Click here for Map
  • Contact Event Host
  • Starts 08 October 2026 04:31 PM UTC
  • Ends 19 October 2026 10:00 PM UTC
  • Admission fee ?

  Speakers

Lokanatha of Verizon

Topic:

FedLoRA-C: Communication-Efficient Federated Fine-Tuning of Large Language Models via Selective Layer Compression

Biography:

Bio: Lokanatha Reddy Gandikota is a Distinguished Engineer at Verizon, Dallas, TX, with over 17 years of experience in software development, AI, and large-scale enterprise systems. His recent work focuses on federated learning, LLM efficiency, and communication-efficient techniques for adapting large language models across distributed environments without centralizing sensitive data. He has published research papers in IEEE and Springer venues and holds a pending patent through Verizon in the AI domain. Lokanatha is an IEEE Senior Member and an IETE Fellow, actively engaged in bridging academic research with real-world industrial applications. At this IEEE Dallas CVT Chapter meeting, he will present his work on FedLoRA-C, which received the Best Industrial Paper Award at IEEE AIS 2026.

Email:




Agenda

Food/Lunch:
Lunch is available only to those who pre-register prior to the meeting.  Sorry, we have to pre-order and consider the costs of meals.

Cost for lunch:

Level of Membership    Prepaid      Pay at Event
UTD student with ID      $2.00         $2.00 
IEEE Member                  $10.00       $15.00 
IEEE Senior Member      $10.00       $15.00 
IEEE Life Member           $5.00      $10.00 
Non-member                 $15.00       $20.00 

 Please look for your specific Member type in the Payment portion of the Registration process (Life, Senior, Regular Member, etc.).

(First 5 Students who have registered in vTools as recorded within vTools date/time stamp on the registration will be given their $2 back at the event, provided they attend. Also, all students must show their UT Dallas ID at the desk on the day of the meetings.)

 

 


Parking passes will be available to those who register, and lunch will be available for a fee.

You do NOT need to be an IEEE member to attend these presentations.