activity
20192025
most citedRelating Graph Neural Networks to Structural Causal Models

14 citations · 24 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2021

The Causal Loss: Driving Correlation to Imply Causation

Moritz Willig, Matej Zečević, Devendra Singh Dhami +1

Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance. Although success has been observed in ma…

cs.LG202114 cited

Relating Graph Neural Networks to Structural Causal Models

Matej Zečević, Devendra Singh Dhami, Petar Veličković +1

Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. For most processes of…

cs.LG20211 cited

Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits

Zhongjie Yu, Devendra Singh Dhami, Kristian Kersting

Probabilistic circuits (PCs) have become the de-facto standard for learning and inference in probabilistic modeling. We introduce Sum-Product-Attention Networks (SPAN), a new gener…

cs.LG2021

Predicting Drug-Drug Interactions from Heterogeneous Data: An Embedding Approach

Devendra Singh Dhami, Siwen Yan, Gautam Kunapuli +2

Predicting and discovering drug-drug interactions (DDIs) using machine learning has been studied extensively. However, most of the approaches have focused on text data or textual r…

cs.LG2021

Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models

Matej Zečević, Devendra Singh Dhami, Athresh Karanam +2

While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference. As a step towards tractable causal models, we consid…

cs.LG2021

A Statistical Relational Approach to Learning Distance-based GCNs

Devendra Singh Dhami, Siwen Yan, Sriraam Natarajan

We consider the problem of learning distance-based Graph Convolutional Networks (GCNs) for relational data. Specifically, we first embed the original graph into the Euclidean space…