SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.12774 · 2019

Routing Networks and the Challenges of Modular and Compositional Computation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
cle-ros/RoutingNetworks pwc_unofficial 2 of 2
FunctionStatusWhere it lives
entropy Ran cle-ros/RoutingNetworks/PytorchRouting/DecisionLayers/Others/RELAX.py
code served (permissive licence) · get_code("a415d1da67633beb")
make_samples Ran cle-ros/RoutingNetworks/PytorchRouting/DecisionLayers/Others/RELAX.py
code served (permissive licence) · get_code("f7a44e38add17d09")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality. Recent work has shown that compositional solutions can be learned and offer substantial gains across a variety of domains, including multi-task learning, language modeling, visual question answering, machine comprehension, and others. However, such models present unique challenges during training when both the module parameters and their composition must be learned jointly. In this paper, we identify several of these issues and analyze their underlying causes. Our discussion focuses on routing networks, a general approach to this problem, and examines empirically the interplay of these challenges and a variety of design decisions. In particular, we consider the effect of how the algorithm decides on module composition, how the algorithm updates the modules, and if the algorithm uses regularization.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1904.12774")
get_code_for_paper("1904.12774")
have("1904.12774")

Connect an agent — have() is free.