Symmetrical SyncMap for Imbalanced General Chunking Problems

Abstract

Recently, SyncMap pioneered an approach to learn complex structures from sequences as well as adapt to any changes in underlying structures. This is achieved by using only nonlinear dynamical equations inspired by neuron group behaviors, i.e., without loss functions. Here we propose Symmetrical SyncMap that goes beyond the original work to show how to create dynamical equations and attractor-repeller points which are stable over the long run, even dealing with imbalanced continual general chunking problems (CGCPs). The main idea is to apply equal updates from negative and positive feedback loops by symmetrical activation. We then introduce the concept of memory window to allow for more positive updates. Our algorithm surpasses or ties other unsupervised state-of-the-art baselines in all 12 imbalanced CGCPs with various difficulties, including dynamically changing ones. To verify its performance in real-world scenarios, we conduct experiments on several well-studied structure learning problems. The proposed method surpasses substantially other methods in 3 out of 4 scenarios, suggesting that symmetrical activation plays a critical role in uncovering topological structures and even hierarchies encoded in temporal data.

arXiv comment40 pages, 19 figures

References in corpus (9)

• Efficient Estimation of Word Representations in Vector Space
• Fast unfolding of communities in large networks
• Finding and evaluating community structure in networks
• Community detection in graphs
• DeepWalk: Online Learning of Social Representations
• Cooperative Game Theory Approaches for Network Partitioning
• Defining and identifying communities in networks
• Analysis of the structure of complex networks at different resolution levels
• A Review of Stochastic Block Models and Extensions for Graph Clustering