directed acyclic graph
A directed acyclic graph (DAG) is a finite graph that consists of vertices connected by edges, where edges have a direction and there are no cycles. In AI, DAGs are often used to represent probabilistic models, dependencies, or computation graphs in deep learning.
- AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
- Graph-based Symbolic Regression with Invariance and Constraint Encoding
- Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
- Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs
- Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
- Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation
- msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML