liveBook · Manning

Federated learning

As explained in Build AI Drug Discovery Pipelines

Federated learning trains a shared model across decentralized datasets while keeping the underlying data at its original sites.

Federated learning trains a shared model across decentralized pharmaceutical datasets without moving the underlying data from the organizations that hold it. It addresses proprietary data silos containing compounds synthesized, measured properties, clinical trials, and negative results. section 13.4.3

A practical deployment must address:

  • Model convergence: distributed training may fail to converge reliably across organizations. section 13.4.3
  • Information leakage: sharing model updates can expose information despite keeping source datasets private. section 13.4.3
  • Data imbalance: private datasets may contain inactive compounds, toxicity results, or other negative outcomes missing from public collections. section 13.4.3

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Identifies the approach and its convergence and leakage challenges without detailing the training protocol or privacy mechanisms.
Examples
Uses pharmaceutical records of synthesized compounds, measured properties, clinical trials, inactive compounds, and toxicity results.
What you can do after
Evaluate collaborative training as a potential response to proprietary data silos while checking convergence and information leakage.
How it connects
Connects drug discovery with proprietary data, negative results, model convergence, and information leakage.

Also explained in

Compare how 2 books explain federated learning →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.