Add weighted loss to factorization machines#1213

Closed

zhenghaoz wants to merge 26 commits into

gorse-io:masterfrom

zhenghaoz:afm-weighted-training

Commits on May 15, 2026

docs: add AFM weighted training development plan
zhenghaoz
committed
docs: update AFM weighted training plan with expression-based weight config
zhenghaoz
committed
docs: use expr-lang/expr for weight expression parsing
zhenghaoz
committed
feat: add feedback_weight config for weighted training
zhenghaoz
committed
docs: mark Phase 2 (config extension) as completed
zhenghaoz
committed
docs: refactor architecture - model layer should not be aware of WeightExpression
zhenghaoz
committed
docs: simplify design - inline expression parsing in Dataset construction
zhenghaoz
committed
feat: add weight expression parsing with expr-lang/expr
zhenghaoz
committed
docs: mark Phase 1 (expression parsing) as completed
zhenghaoz
committed
feat: add weight support to Dataset
zhenghaoz
committed
docs: mark Phase 3 (data layer extension) as completed
zhenghaoz
committed
feat: add weighted training support to AFM
zhenghaoz
committed
docs: mark Phase 4 (model layer extension) as partially completed
zhenghaoz
committed
test: add weighted training test for AFM
zhenghaoz
committed
docs: mark Phase 5 (testing) as completed
zhenghaoz
committed
fix: correct import order in model/ctr tests
zhenghaoz
committed
fix: use tagged switch instead of if-else (staticcheck QF1003)
zhenghaoz
committed
feat: add weighted feedback support for item-to-item recommendation
zhenghaoz
committed
refactor: move weight functions to common/weight package
zhenghaoz
committed
test: remove TestFactorizationMachines_WeightedTraining
zhenghaoz
committed
refactor: move weight functions from model/ctr to logics package
zhenghaoz
committed
refactor: simplify ctr.Dataset to only keep SampleWeights
zhenghaoz
committed
refactor: rename SampleWeights to Weights in ctr.Dataset
zhenghaoz
committed
refactor: update weight test tolerance type and clean up unused imports in tests
zhenghaoz
committed
feat: add FeedbackWeightExpression and related tests for dynamic weight evaluation
zhenghaoz
committed
feat: integrate FeedbackWeightExpression into Recommender and simplify Evaluate method
zhenghaoz
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add weighted loss to factorization machines#1213

Add weighted loss to factorization machines#1213
zhenghaoz wants to merge 26 commits into
gorse-io:masterfrom
zhenghaoz:afm-weighted-training

Commits on May 15, 2026

docs: add AFM weighted training development plan

docs: update AFM weighted training plan with expression-based weight config

docs: use expr-lang/expr for weight expression parsing

feat: add feedback_weight config for weighted training

docs: mark Phase 2 (config extension) as completed

docs: refactor architecture - model layer should not be aware of WeightExpression

docs: simplify design - inline expression parsing in Dataset construction

feat: add weight expression parsing with expr-lang/expr

docs: mark Phase 1 (expression parsing) as completed

feat: add weight support to Dataset

docs: mark Phase 3 (data layer extension) as completed

feat: add weighted training support to AFM

docs: mark Phase 4 (model layer extension) as partially completed

test: add weighted training test for AFM

docs: mark Phase 5 (testing) as completed

fix: correct import order in model/ctr tests

fix: use tagged switch instead of if-else (staticcheck QF1003)

feat: add weighted feedback support for item-to-item recommendation

refactor: move weight functions to common/weight package

test: remove TestFactorizationMachines_WeightedTraining

refactor: move weight functions from model/ctr to logics package

refactor: simplify ctr.Dataset to only keep SampleWeights

refactor: rename SampleWeights to Weights in ctr.Dataset

refactor: update weight test tolerance type and clean up unused imports in tests

feat: add FeedbackWeightExpression and related tests for dynamic weight evaluation

feat: integrate FeedbackWeightExpression into Recommender and simplify Evaluate method