Characterizable Invertible $3\times3$  Convolution

**Slow Momentum** (SlowMo) is a distributed optimization method where workers periodically synchronize and perform a momentum update, after multiple iterations of a base optimization algorithm.  Periodically, after taking some number $\tau$ of base algorithm steps, workers average their parameters using ALLREDUCE and perform a momentum update.

SlowMo

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

CInC Flow

CInC Flow: Characterizable Invertible 3x3 Convolution

Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs—both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups.

Description and image from: [DEEP GRAPH INFOMAX](https://arxiv.org/pdf/1809.10341.pdf)

Source	CInC Flow: Characterizable Invertible 3x3 Convolution
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com