Self-Directed Task Identification

TL;DR

This paper introduces SDTI, a novel neural network framework enabling models to autonomously identify target variables in datasets without pre-training, reducing manual annotation efforts.

Contribution

The paper presents a minimal, interpretable architecture for zero-shot target identification, demonstrating its effectiveness on benchmark tasks and outperforming baselines.

Findings

SDTI outperforms baseline architectures by 14% in F1 score.

SDTI reliably identifies the correct target variable in various benchmarks.

The framework reduces reliance on manual data annotation.

Abstract

In this work, we present a novel machine learning framework called Self-Directed Task Identification (SDTI), which enables models to autonomously identify the correct target variable for each dataset in a zero-shot setting without pre-training. SDTI is a minimal, interpretable framework demonstrating the feasibility of repurposing core machine learning concepts for a novel task structure. To our knowledge, no existing architectures have demonstrated this ability. Traditional approaches lack this capability, leaving data annotation as a time-consuming process that relies heavily on human effort. Using only standard neural network components, we show that SDTI can be achieved through appropriate problem formulation and architectural design. We evaluate the proposed framework on a range of benchmark tasks and demonstrate its effectiveness in reliably identifying the ground truth out of a set of potential target variables. SDTI outperformed baseline architectures by 14% in F1 score on synthetic task identification benchmarks. These proof-of-concept experiments highlight the future potential of SDTI to reduce dependence on manual annotation and to enhance the scalability of autonomous learning systems in real-world applications.