MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System

• URL: http://arxiv.org/abs/2411.11871v1
• Date: Sun, 03 Nov 2024 21:20:21 GMT
• Title: MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System
• Authors: Yun He, Xuxing Chen, Jiayi Xu, Renqin Cai, Yiling You, Jennifer Cao, Minhui Huang, Liu Yang, Yiqun Liu, Xiaoyi Liu, Rong Jin, Sem Park, Bo Long, Xue Feng,
• Abstract summary: We propose a gradient balancing approach called MultiBalance for industrial-scale multi-task recommendation systems. It balances the per-task gradients to alleviate the negative transfer, while saving the huge cost for grid search or manual explorations. We conduct experiments on Meta's large-scale ads and feeds multi-task recommendation system, and observe that MultiBalance achieves significant gains.
• Score: 28.23029744894405
• License:
• Abstract: In industrial recommendation systems, multi-task learning (learning multiple tasks simultaneously on a single model) is a predominant approach to save training/serving resources and improve recommendation performance via knowledge transfer between the joint learning tasks. However, multi-task learning often suffers from negative transfer: one or several tasks are less optimized than training them separately. To carefully balance the optimization, we propose a gradient balancing approach called MultiBalance, which is suitable for industrial-scale multi-task recommendation systems. It balances the per-task gradients to alleviate the negative transfer, while saving the huge cost for grid search or manual explorations for appropriate task weights. Moreover, compared with prior work that normally balance the per-task gradients of shared parameters, MultiBalance is more efficient since only requiring to access per-task gradients with respect to the shared feature representations. We conduct experiments on Meta's large-scale ads and feeds multi-task recommendation system, and observe that MultiBalance achieves significant gains (e.g., 0.738% improvement for normalized entropy (NE)) with neutral training cost in Queries Per Second (QPS), which is significantly more efficient than prior methods that balance per-task gradients of shared parameters with 70~80% QPS degradation.

Related papers

• Personalized Multi-task Training for Recommender System [80.23030752707916]
  PMTRec is the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources. Our contributions open new avenues for advancing personalized multi-task training in recommender systems.
  arXiv  Detail & Related papers  (2024-07-31T06:27:06Z)
• Scalarization for Multi-Task and Multi-Domain Learning at Scale [15.545810422759295]
  Training a single model on multiple input domains and/or output tasks allows for compressing information from multiple sources into a unified backbone. However, optimizing such networks is a challenge due to discrepancies between the different tasks or domains.
  arXiv  Detail & Related papers  (2023-10-13T07:31:04Z)
• Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies [0.981328290471248]
  Multi-Task Learning (MTL) is a growing subject of interest in deep learning. MTL can be impractical as certain tasks can dominate training and hurt performance in others. We propose techniques for loss balancing based on scaling by the exponential moving average.
  arXiv  Detail & Related papers  (2022-11-22T09:22:48Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• In Defense of the Unitary Scalarization for Deep Multi-Task Learning [121.76421174107463]
  We present a theoretical analysis suggesting that many specialized multi-tasks can be interpreted as forms of regularization. We show that, when coupled with standard regularization and stabilization techniques, unitary scalarization matches or improves upon the performance of complex multitasks.
  arXiv  Detail & Related papers  (2022-01-11T18:44:17Z)
• SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning [0.0]
  Multi-task learning (MTL) is a subfield of machine learning with important applications. The best MTL optimization methods require individually computing the gradient of each task's loss function. We propose Scaled Loss Approximate Weighting (SLAW), a method for multi-task optimization that matches the performance of the best existing methods while being much more efficient.
  arXiv  Detail & Related papers  (2021-09-16T20:58:40Z)
• HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks [4.095907708855597]
  Multi-task learning (MTL) can improve performance on a task by sharing representations with one or more related auxiliary-tasks. Usually, MTL-networks are trained on a composite loss function formed by a constant weighted combination of the separate task losses. In practice, constant loss weights lead to poor results for two reasons: (i) for mini-batch based optimisation, the optimal task weights vary significantly from one update to the next depending on mini-batch sample composition. We introduce HydaLearn, an intelligent weighting algorithm that connects main-task gain to the individual task gradients, in order to inform
  arXiv  Detail & Related papers  (2020-08-26T16:04:02Z)
• Small Towers Make Big Differences [59.243296878666285]
  Multi-task learning aims at solving multiple machine learning tasks at the same time. A good solution to a multi-task learning problem should be generalizable in addition to being Pareto optimal. We propose a method of under- parameterized self-auxiliaries for multi-task models to achieve the best of both worlds.
  arXiv  Detail & Related papers  (2020-08-13T10:45:31Z)
• Gradient Surgery for Multi-Task Learning [119.675492088251]
  Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a conflicting gradient.
  arXiv  Detail & Related papers  (2020-01-19T06:33:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.