AHP: Learning to Negative Sample for Hyperedge Prediction

04/13/2022
by   Hyunjin Hwang, et al.
0

Hypergraphs (i.e., sets of hyperedges) naturally represent group relations (e.g., researchers co-authoring a paper and ingredients used together in a recipe), each of which corresponds to a hyperedge (i.e., a subset of nodes). Predicting future or missing hyperedges bears significant implications for many applications (e.g., collaboration and recipe recommendation). What makes hyperedge prediction particularly challenging is the vast number of non-hyperedge subsets, which grows exponentially with the number of nodes. Since it is prohibitive to use all of them as negative examples for model training, it is inevitable to sample a very small portion of them, and to this end, heuristic sampling schemes have been employed. However, trained models suffer from poor generalization capability for examples of different natures. In this paper, we propose AHP, an adversarial training-based hyperedge-prediction method. It learns to sample negative examples without relying on any heuristic schemes. Using six real hypergraphs, we show that AHP generalizes better to negative examples of various natures. It yields up to 28.2 its variants with sampling schemes tailored to test sets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/02/2022

Negative Sampling for Recommendation

How to effectively sample high-quality negative instances is important f...
research
05/27/2021

Rethinking InfoNCE: How Many Negative Samples Do You Need?

InfoNCE loss is a widely used loss function for contrastive model traini...
research
02/14/2021

Relation-aware Graph Attention Model With Adaptive Self-adversarial Training

This paper describes an end-to-end solution for the relationship predict...
research
07/13/2023

NS4AR: A new, focused on sampling areas sampling method in graphical recommendation Systems

The effectiveness of graphical recommender system depends on the quantit...
research
03/27/2016

Negative Learning Rates and P-Learning

We present a method of training a differentiable function approximator f...
research
07/12/2017

Negative Sampling Improves Hypernymy Extraction Based on Projection Learning

We present a new approach to extraction of hypernyms based on projection...
research
12/05/2018

Random Spiking and Systematic Evaluation of Defenses Against Adversarial Examples

Image classifiers often suffer from adversarial examples, which are gene...

Please sign up or login with your details

Forgot password? Click here to reset