Goto

Collaborating Authors

Lovasz Convolutional Networks

arXiv.org Machine Learning

Semi-supervised learning on graph structured data has received significant attention with the recent introduction of graph convolution networks (GCN). While traditional methods have focused on optimizing a loss augmented with Laplacian regularization framework, GCNs perform an implicit Laplacian type regularization to capture local graph structure. In this work, we propose Lovasz convolutional network (LCNs) which are capable of incorporating global graph properties. LCNs achieve this by utilizing Lovasz's orthonormal embeddings of the nodes. We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs. We validate the proposed method on standard random graph models such as stochastic block models (SBM) and certain community structure based graphs where LCNs outperform GCNs and learn more intuitive embeddings. We also perform extensive binary and multi-class classification experiments on real world datasets to demonstrate LCN's effectiveness. In addition to simple graphs, we also demonstrate the use of LCNs on hypergraphs by identifying settings where they are expected to work better than GCNs.


In Search of God's Mathematical Perfect Proofs

WIRED

Paul Erdős, the famously eccentric, peripatetic and prolific 20th-century mathematician, was fond of the idea that God has a celestial volume containing the perfect proof of every mathematical theorem. "This one is from The Book," he would declare when he wanted to bestow his highest praise on a beautiful proof. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences. Never mind that Erdős doubted God's very existence. "You don't have to believe in God, but you should believe in The Book," Erdős explained to other mathematicians.


Hypergraph Learning with Line Expansion

arXiv.org Machine Learning

Previous hypergraph expansions are solely carried out on either vertex level or hyperedge level, thereby missing the symmetric nature of data co-occurrence, and resulting in information loss. To address the problem, this paper treats vertices and hyperedges equally and proposes a new hypergraph formulation named the \emph{line expansion (LE)} for hypergraphs learning. The new expansion bijectively induces a homogeneous structure from the hypergraph by treating vertex-hyperedge pairs as "line nodes". By reducing the hypergraph to a simple graph, the proposed \emph{line expansion} makes existing graph learning algorithms compatible with the higher-order structure and has been proven as a unifying framework for various hypergraph expansions. We evaluate the proposed line expansion on five hypergraph datasets, the results show that our method beats SOTA baselines by a significant margin.


The HyperTrac Project: Recent Progress and Future Research Directions on Hypergraph Decompositions

arXiv.org Artificial Intelligence

Constraint Satisfaction Problems (CSPs) play a central role in many applications in Artificial Intelligence and Operations Research. In general, solving CSPs is NP-complete. The structure of CSPs is best described by hypergraphs. Therefore, various forms of hypergraph decompositions have been proposed in the literature to identify tractable fragments of CSPs. However, also the computation of a concrete hypergraph decomposition is a challenging task in itself. In this paper, we report on recent progress in the study of hypergraph decompositions and we outline several directions for future research.


Learning with Hypergraphs: Clustering, Classification, and Embedding

Neural Information Processing Systems

We usually endow the investigated objects with pairwise relationships, which can be illustrated as graphs. In many real-world problems, however, relationships among the objects of our interest are more complex than pairwise. Naivelysqueezing the complex relationships into pairwise ones will inevitably lead to loss of information which can be expected valuable for our learning tasks however. Therefore we consider using hypergraphs instead tocompletely represent complex relationships among the objects of our interest, and thus the problem of learning with hypergraphs arises. Our main contribution in this paper is to generalize the powerful methodology of spectral clustering which originally operates on undirected graphs to hypergraphs, andfurther develop algorithms for hypergraph embedding and transductive classification on the basis of the spectral hypergraph clustering approach.Our experiments on a number of benchmarks showed the advantages of hypergraphs over usual graphs.