BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024533Z
LOCATION:3000\, Level 3
DTSTART;TZID=America/Los_Angeles:20250625T103000
DTEND;TZID=America/Los_Angeles:20250625T104500
UID:dac_DAC 2025_sess106_RESEARCH1429@linklings.com
SUMMARY:Few-shot Learning on AMS Circuits and Its Application to Parasitic
  Capacitance Prediction
DESCRIPTION:Shan Shen, Yibin Zhang, Hector Rodriguez, and Wenjian Yu (Tsin
 ghua University)\n\nGraph representation learning is a powerful approach t
 o extract features from graph-structured data such as analog/mixed-signal 
 (AMS) circuits. However, the training of deep learning models for AMS desi
 gn is severely limited by the scarcity of integrated circuit design data. 
 In this work, we present CirGPS, a few-shot learning method for parasitic 
 effect prediction in AMS circuits. The circuit netlist is modeled as a het
 erogeneous graph while the coupling capacitance is modeled as a link. CirG
 PS is pre-trained on link prediction and fine-tuned on edge regression. Th
 e proposed method starts with a small-hop sampling technique that converts
  a link or a node into a subgraph. Then, the subgraph embeddings are learn
 ed with a hybrid graph Transformer.  Additionally, CirGPS integrates a low
 -cost positional encoding that summarizes the positional and structural in
 formation of the target link. CirGPS improves the accuracy of coupling exi
 stence by at least 20% and reduces the MAE of capacitance estimation by at
  least 0.067 compared to existing methods. Our method naturally has good s
 calability and can be applied with zero-shot learning to a wide variety of
  AMS designs. Through our ablation studies, we provide valuable insights i
 nto graph models for representation learning.\n\nTopics: AI\n\nTracks: AI2
 : AI/ML Application and Infrastructure\n\nSession Chairs: Jun Shiomi (The 
 University of Osaka) and Subhajit Dutta Chowdhury (Advanced Micro Devices 
 (AMD))\n\n
END:VEVENT
END:VCALENDAR