AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

A Multi-Channel Neural Graphical Event Model with Negative Evidence

Tian Gao, Dharmashankar Subramanian, Karthikeyan Shanmugam, Debarun Bhattacharjya, Nicholas Mattei

AAAI 2020 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neural point-process models · 8 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 fake epochs to reinforce intervals with no observed eventsMCN-GEM · PGEM synthetic datasetslog-likelihoodImproved
Add fake epochsMCN-GEM · ICEWS Argentina, Brazil, Colombia, Mexicolog-likelihoodImproved
Add fake epochsMCN-GEM · ICEWS Venezuelalog-likelihoodHurt
Add one fake epoch instead of none (ablation)MCN-GEM · ICEWS Argentinalog-likelihood: -3559.5 -> -2677.9Improved
Use two fake epochs instead of one (ablation)MCN-GEM · ICEWS Argentinalog-likelihood: -2677.9 -> -2652.3Improved
Use three, four, or five fake epochs instead of one (ablation)MCN-GEM · ICEWS Argentinalog-likelihood: -2677.9 -> -2772.1; -2803.1; -2881.0Hurt
Use multi-channel rather than single-channel hidden states (ablation)MCN-GEM · ICEWS Argentinalog-likelihoodImproved
Add one fake epoch to the single-channel version (ablation)MCN-GEM single-channel variant · ICEWS Argentinalog-likelihood: -4323.8±35.4 -> -3839.4.9±25.4Improved
Add one fake epoch to the multi-channel version (ablation)MCN-GEM · ICEWS Argentinalog-likelihood: -4282.2±58.1 -> -3302.6±28.1Improved
Add attention with memory size 1, 2, or 3 (ablation)MCN-GEM with one fake epoch · ICEWS Argentinalog-likelihood: -3302.6±28.1 -> -2841.0±23.5; -2693.9± 27.0; -2682.6±29.3Improved
Increase attention memory size from 3 to 5 or 10 (ablation)MCN-GEM with one fake epoch · ICEWS Argentinalog-likelihood: -2682.6±29.3 -> -2871.8±126.9; -2947.3 ± 190.0Hurt
Use the full MCN-GEM model instead of MCN-noFMCN-GEM · MIMIClog-likelihood: -1380.4 -> -837.4Improved

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