ExplainableAI

Meet Modules of Influence: finding feature groups in AI decisions

Kari Jaaskelainen

04 Nov 2025 — 1 min read

Meet “Modules of Influence”: groups of features that drive AI decisions

Most explainers like SHAP or LIME tell you which single features mattered for one prediction. This paper goes a step further: it builds an explanation graph across many predictions and uses community detection to reveal feature groups that act together.

See which features consistently team up to push outcomes.
Debug faster with module-level ablations (turn groups off/on, not just one feature).
Localize bias exposure to specific modules instead of blaming the whole model.
Check redundancy and causality patterns with new stability and synergy metrics.

Across synthetic and real datasets, the approach uncovers correlated feature clusters and makes model behavior easier to reason about—at the level where decisions actually happen: groups, not isolated inputs. Includes code and benchmarks for module discovery.

Paper by Ehsan Moradi. Read more: http://arxiv.org/abs/2510.27655v1

Paper: http://arxiv.org/abs/2510.27655v1

Register: https://www.AiFeta.com

ExplainableAI XAI MachineLearning AITransparency ModelInterpretability SHAP LIME Graphs CommunityDetection ResponsibleAI

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)