Algorithmic Acceleration of Parallel ALS for Collaborative Filtering:\n Speeding up Distributed Big Data Recommendation in Spark
Bibliographic record
Abstract
Collaborative filtering algorithms are important building blocks in many\npractical recommendation systems. For example, many large-scale data processing\nenvironments include collaborative filtering models for which the Alternating\nLeast Squares (ALS) algorithm is used to compute latent factor matrix\ndecompositions. In this paper, we propose an approach to accelerate the\nconvergence of parallel ALS-based optimization methods for collaborative\nfiltering using a nonlinear conjugate gradient (NCG) wrapper around the ALS\niterations. We also provide a parallel implementation of the accelerated\nALS-NCG algorithm in the Apache Spark distributed data processing environment,\nand an efficient line search technique as part of the ALS-NCG implementation\nthat requires only one pass over the data on distributed datasets. In serial\nnumerical experiments on a linux workstation and parallel numerical experiments\non a 16 node cluster with 256 computing cores, we demonstrate that the combined\nALS-NCG method requires many fewer iterations and less time than standalone ALS\nto reach movie rankings with high accuracy on the MovieLens 20M dataset. In\nparallel, ALS-NCG can achieve an acceleration factor of 4 or greater in clock\ntime when an accurate solution is desired; furthermore, the acceleration factor\nincreases as greater numerical precision is required in the solution. In\naddition, the NCG acceleration mechanism is efficient in parallel and scales\nlinearly with problem size on synthetic datasets with up to nearly 1 billion\nratings. The acceleration mechanism is general and may also be applicable to\nother optimization methods for collaborative filtering.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".