AIJan 5, 2018

Intelligence Graph

arXiv:1801.01604v12 citations
Originality Incremental advance
AI Analysis

This addresses the problem of integrating diverse AI methods for building more powerful systems, though it appears incremental as it combines existing paradigms rather than introducing a fundamentally new one.

The paper tackles the incompatibility between logic, neural, and probabilistic intelligence architectures by proposing the intelligence graph (iGraph), which integrates these approaches under a forward-backward propagation framework, and demonstrates its effectiveness by beating state-of-the-art baselines in a recommendation model.

In fact, there exist three genres of intelligence architectures: logics (e.g. \textit{Random Forest, A$^*$ Searching}), neurons (e.g. \textit{CNN, LSTM}) and probabilities (e.g. \textit{Naive Bayes, HMM}), all of which are incompatible to each other. However, to construct powerful intelligence systems with various methods, we propose the intelligence graph (short as \textbf{\textit{iGraph}}), which is composed by both of neural and probabilistic graph, under the framework of forward-backward propagation. By the paradigm of iGraph, we design a recommendation model with semantic principle. First, the probabilistic distributions of categories are generated from the embedding representations of users/items, in the manner of neurons. Second, the probabilistic graph infers the distributions of features, in the manner of probabilities. Last, for the recommendation diversity, we perform an expectation computation then conduct a logic judgment, in the manner of logics. Experimentally, we beat the state-of-the-art baselines and verify our conclusions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes