When Does Label Propagation Fail? A View from a Network Generative Model
نویسندگان
چکیده
What kinds of data does Label Propagation (LP) work best on? Can we justify the solution of LP from a theoretical standpoint? LP is a semisupervised learning algorithm that is widely used to predict unobserved node labels on a network (e.g., user’s gender on an SNS). Despite its importance, its theoretical properties remain mostly unexplored. In this paper, we answer the above questions by interpreting LP from a statistical viewpoint. As our main result, we identify the network generative model behind the discretized version of LP (DLP), and we show that under specific conditions the solution of DLP is equal to the maximum a posteriori estimate of that generative model. Our main result reveals the critical limitations of LP. Specifically, we discover that LP would not work best on networks with (1) disassortative node labels, (2) clusters having different edge densities, (3) nonuniform label distributions, or (4) unreliable node labels provided. Our experiments under a variety of settings support our theoretical results.
منابع مشابه
Socratic Learning: Correcting Misspecified Generative Models using Discriminative Models
A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to label training data. Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy pa...
متن کاملMany Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Generative adversarial networks (GANs) are a family of generative models that do not minimize a single training criterion. Unlike other generative models, the data distribution is learned via a game between a generator (the generative model) and a discriminator (a teacher providing training signal) that each minimize their own cost. GANs are designed to reach a Nash equilibrium at which each pl...
متن کاملAlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
Recently, several methods based on generative adversarial network (GAN) have been proposed for the task of aligning cross-domain images or learning a joint distribution of cross-domain images. One of the methods is to use conditional GAN for alignment. However, previous attempts of adopting conditional GAN do not perform as well as other methods. In this work we present an approach for improvin...
متن کاملANN Based Modeling for Prediction of Evaporation in Reservoirs (RESEARCH NOTE)
This paper is an attempt to assess the potential and usefulness of ANN based modeling for evaporation prediction from a reservoir, where in classical and empirical equations failed to predict the evaporation accurately. The meteorological data set of daily pan evaporation, temperature, solar radiation, relative humidity, wind speed is used in this study. The performance of feed forward back pro...
متن کاملA Generative Model with Network Regularization for Semi-Supervised Collective Classification
In recent years much effort has been devoted to Collective Classification (CC) techniques for predicting labels of linked instances. Given a large number of labeled data, conventional CC algorithms can make use of local labeled neighbours to increase accuracy. However, in many real-world applications, labeled data are limited and very expensive to obtain. In this situation, most of the data hav...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017