AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Pairwise Causality Guided Transformers for Event Sequences

Xiao Shou, Debarun Bhattacharjya, Tian Gao, Dharmashankar Subramanian, Oktie Hassanzadeh, Kristin Bennett

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add one pairwise causal statement via PC-TES lossTES transformer · Synth-1test log-likelihood: -107.81 -> -107.19Improved
add one pairwise causal statement via PC-TES lossTES transformer · Synth-2test log-likelihood: -114.01 -> -111.89Improved
add one pairwise causal statement via PC-TES lossTES transformer · Synth-3test log-likelihood: -119.99 -> -113.58Improved
add one pairwise causal statement via PC-TES lossTES transformer · Synth-4test log-likelihood: -113.95 -> -113.15No clear effect
add causal statements via PC-TESTES transformer · Defitest log-likelihood: -126.56 -> -120.54Improved
add causal statements via PC-TESTES transformer · Diabetestest log-likelihood: -373.27 -> -370.64Improved
add causal statements via PC-TESTES transformer · Linkedintest log-likelihood: -22.48 -> -21.71Improved
add causal statements via PC-TESTES transformer · Beigebookstest log-likelihood: -10.27 -> -10.04Improved
use transformer TES instead of attention-based PAINevent sequence model · Synth-1test log-likelihood: -141.06 -> -107.81Improved
use neural models instead of parametric BSuMM/OSuMM/kMCevent sequence model · Synth-1test log-likelihood: -373.85 -> -107.81Improved
inject tsunami -> earthquake pair into PC-TESPC-TES · LLM-generated event sequencestest log-likelihood: -28.29 -> -27.48Improved
inject impeachment -> protest pair into PC-TESPC-TES · LLM-generated event sequencestest log-likelihood: -28.29 -> -28.19No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy