v0.14.0

[ValerianRey]

🍉 UW, IMTL-L

This release introduces UW and IMTL-L, two very similar scalarization methods. Thanks a lot to @ppraneth for the contributions!

We also thank @KhusPatel4450 for becoming code owner of the aggregation package and @ppraneth for becoming code owner of the scalarization package. This should make the project slightly more decentralized.

Changelog

Added

• Added IMTL-L (the loss-balancing variant of Impartial Multi-Task Learning) from Towards
  Impartial Multi-Task Learning (ICLR 2021), a stateful
  Scalarizer that learns a per-task scale s_i and combines the values as
  Σ (exp(s_i) · L_i − s_i).
• Added UW (Uncertainty Weighting) from Multi-Task Learning Using Uncertainty to Weigh Losses
  for Scene Geometry and
  Semantics,
  a Scalarizer that combines the values using learned per-task uncertainties. It is the first
  stateful, trainable scalarizer: its log-variances are an nn.Parameter that must be passed to
  the optimizer.

---

This discussion was created from the release v0.14.0.