Skip to content

Latest commit

 

History

History
89 lines (67 loc) · 6.08 KB

CHANGELOG.md

File metadata and controls

89 lines (67 loc) · 6.08 KB

November 2022

October 2022

  • PR #265: implementation of regularization by N3 norm (thanks @Kenkoko)

July 2022

  • PR #263: fixed bug in application of penalty to models with reciprocal relations (thanks @Kenkoko)

October 2021

  • 5127cf2: Fix differences in TransE scoring implementations

September 2021

  • PR #224: Take floating point issues into account for tie calculation in entity-ranking (thanks @sfschouten)

June 2021

  • 9a4f69a: Refactor time measurement with new timer class

March 2021

  • PR #191: Fix loading of pretrained embeddings with reciprocal relation models

February 2021

  • 27e8a32: improve validation time by allowing bulk KvsAll index lookup and improved history computation
  • PR #154: store checkpoint containing the initialized model for reproducibility
  • 9e88117: Add Transformer model and learning rate warmup (thanks nluedema)
  • PR #176: Add TransH model (thanks Mayo42)

December 2020

  • PR #164: Allow to easily add custom training/evaluation/search jobs
  • PR #159: Add a plugin mechanism (thanks @sfschouten)
  • PR #157: Add CoDEx datasets and pretrained models (thanks @tsafavi)

November 2020

  • PR #155: Faster reading of triple files

October 2020

  • d275419, 87c5463: Support parameter groups with group-specific optimizer args
  • PR #152: Added training loss evaluation job

September 2020

  • PR #147: Support both minimization and maximization of metrics
  • PR #144: Support to tune subbatch size automatically
  • PR #143: Allow processing of large batches in smaller subbatches to save memory

August 2020

  • PR #140: Calculate penalty for entities only once, if subject-embedder == object-embedder
  • PR #138: Revision of hooks, fix of embedding normalization
  • PR #135: Revised sampling API, faster negative sampling with shared samples

June 2020

  • PR #112: Initialize embeddings from a packaged model
  • PR #113: Reduce memory consumption and loading times of large datasets
  • Various smaller improvements and bug fixes

May 2020

  • PR #110: Support for different tie-breaking methods in evaluation (thanks Nzteb)
  • 1d26e63: Add head/tail evaluation per relation type
  • dfd0aac: Added squared error loss (thanks Nzteb)
  • PR #104: Fix incorrect relation type measurement (thanks STayinloves)
  • PR #101: Revise embedder penalty API (thanks Nzteb)
  • PR #94: Support for packaged models (thanks AdrianKS)
  • Improved seeding of workers when a fixed NumPy seed is used
  • Various smaller improvements and bug fixes
  • Added more mappings from entity IDs to names for Freebase datasets (in entity_strings.del file)

Apr 2020

  • Improved shared negative sampling (WOR sampling, exclude positive triples from negative sample)
  • PR #86: Support (s,?,o) queries for KvsAll training (thanks vonVogelstein)

Mar 2020

  • cf64dd2: Fast dataset/index loading via cached pickle files
  • 4bc86b1: Add support for chunking a batch when training with negative sampling
  • 14dc926: Add ability to dump configs in various ways
  • PR #64: Initial support for frequency-based negative sampling (thanks AdrianKS)
  • PR #77: Simpler use of command-line interface (thanks cthoyt)
  • 76a0077: Added RotatE
  • 7235e99: Added option to add a constant offset before computing BCE loss
  • 67de6c5: Added CP
  • a5ee441: Added SimplE

Feb 2020

  • PR #71: Faster and more memory-efficient training with negative sampling (thanks AdrianKS)
  • Initial release