VM

Selected research

All research

Paper explained

PhD proposal Responsible AI

Forgetting Machines: Responsibility by Design in Machine Unlearning

Viktoriia Makovska

What would it take to build models that can forget by design?

The question

Why this work

This PhD proposal connects the meaning of forgetting to the engineering of systems that can unlearn. It asks how to integrate unlearning into data workflows, test its limits, and make future removal intentional and accountable.

The approach

A visual guide

Three connected research directions

  1. Integrate

    Make unlearning part of data preparation, model repair, and evaluation.

  2. Investigate

    Probe residual influence, semantic dependencies, and lost capabilities.

  3. Design

    Build traceability, source separation, and verification into future systems.

Research agenda, not a completion timeline. The three components inform one another rather than forming a fixed sequence. Sections 3–5

What the work contributes

The proposed agenda combines statistical and mechanistic verification with architectural choices such as source separation, provenance tracking, and retained training updates. Mechanistic interpretability is proposed as one way to examine traces that behavior alone may miss.

Sections 3–5

Original paper & resources

PhD Topic Proposal, UCU Applied Sciences Faculty (2025).

Citation
Makovska, V. (2025). Forgetting Machines: Responsibility by Design in Machine Unlearning [PhD topic proposal]. Ukrainian Catholic University.