Provable Pathways: Learning Multiple Tasks over Multiple Paths
Constructing useful representations across a large number of tasks is a key requirement for sample-efficient intelligent systems. A traditional idea in multitask learning (MTL) is building a shared representation across tasks which can then be adapted to new tasks by tuning last layers. A desirable refinement of using a shared one-fits-all representation is to construct task-specific representations. To this end, recent PathNet/muNet architectures represent individual tasks as pathways within a larger supernet. The subnetworks induced by pathways can be viewed as task-specific representations that are composition of modules within supernet's computation graph. This work explores the pathways proposal from the lens of statistical learning: We first develop novel generalization bounds for empirical risk minimization problems learning multiple tasks over multiple paths (Multipath MTL). In conjunction, we formalize the benefits of resulting multipath representation when adapting to new downstream tasks. Our bounds are expressed in terms of Gaussian complexity, lead to tangible guarantees for the class of linear representations, and provide novel insights into the quality and benefits of a multipath representation. When computation graph is a tree, Multipath MTL hierarchically clusters the tasks and builds cluster-specific representations. We provide further discussion and experiments for hierarchical MTL and rigorously identify the conditions under which Multipath MTL is provably superior to traditional MTL approaches with shallow supernets.
Code (0)
등록된 구현이 없습니다.
Tasks
Generalization BoundsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BrainMAP: Learning Multiple Activation Pathways in Brain Networks
Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and com…
MambaMixture-of-ExpertsFramework based on complex networks to model and mine patient pathways
The automatic discovery of a model to represent the history of encounters of a group of patients with the healthcare system -- the so-called "pathway of patients" -- is a new field of research that supports clinical and …
Missing Data Multiple Imputation for Tabular Q-Learning in Online RL
Missing data in online reinforcement learning (RL) poses challenges compared to missing data in standard tabular data or in offline policy learning. The need to impute and act at each time step means that imputation cann…
Reinforcement LearningProvable Model Provenance Set for Large Language Models
The growing prevalence of unauthorized model usage and misattribution has increased the need for reliable model provenance analysis. However, existing methods largely rely on heuristic fingerprint-matching rules that lac…
Improvable Gap Balancing for Multi-Task Learning
In multi-task learning (MTL), gradient balancing has recently attracted more research interest than loss balancing since it often leads to better performance. However, loss balancing is much more efficient than gradient …
Deep Reinforcement LearningMulti-Task Learning