CONCUR:连续约束和无约束路由的框架
CONCUR: A Framework for Continual Constrained and Unconstrained Routing
AI总结:
CONCUR提出了一种支持连续和无约束路由的框架,通过模块化设计和多表示学习提升路由效率与准确性。
摘要:
人工智能任务在复杂性上有所不同,最佳解决方法需要不同的计算策略(例如,模型和解码方法的组合)。因此,一个有效的路由系统,将任务映射到适当的策略至关重要。大多数先前的方法通过在所有策略上训练单个模型来构建路由框架,这要求在新策略出现时必须重新训练,导致高开销。然而,尝试实现连续路由时,往往面临泛化困难。先前的模型通常使用单一的输入表示,限制了它们捕捉路由问题完整复杂性的能力,导致路由决策次优。为了解决这些差距,我们提出了CONCUR,一个支持连续和无约束路由(即带有或不带有预算的路由)的连续路由框架。我们的模块化设计为每个策略训练一个单独的预测模型,使无缝纳入新策略变得可能,同时附加的训练成本很低。我们的预测器还利用任务和计算策略的多种表示,以更好地捕捉整体问题的复杂性。在分布内和分布外、知识密集和推理密集型任务上的实验表明,我们的方法在连续和非连续设置中均优于最佳单一策略和强大的现有路由技术,同时在端到端准确性和推理成本方面表现更优,并且在连续设置中降低了训练成本。
英文摘要:
AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial. Most prior methods build the routing framework by training a single model across all strategies, which demands full retraining whenever new strategies appear and leads to high overhead. Attempts at such continual routing, however, often face difficulties with generalization. Prior models also typically use a single input representation, limiting their ability to capture the full complexity of the routing problem and leading to sub-optimal routing decisions. To address these gaps, we propose CONCUR, a continual routing framework that supports both constrained and unconstrained routing (i.e., routing with or without a budget). Our modular design trains a separate predictor model for each strategy, enabling seamless incorporation of new strategies with low additional training cost. Our predictors also leverage multiple representations of both tasks and computation strategies to better capture overall problem complexity. Experiments on both in-distribution and out-of-distribution, knowledge- and reasoning-intensive tasks show that our method outperforms the best single strategy and strong existing routing techniques with higher end-to-end accuracy and lower inference cost in both continual and non-continual settings, while also reducing training cost in the continual setting.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。