Search Results for author:
Found 47 papers, 24 papers with code
TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains.
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
Pre-trained Vision Transformers now serve as powerful tools for computer vision.
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client's gradient vectors.
Scalable Out-of-distribution Robustness in the Presence of Unobserved Confounders
These conditions create a challenging scenario for OOD robustness: (a) $Z^\text{tr}$ is an unobserved confounder during training, (b) $P^\text{te}{Z} \neq P^\text{tr}{Z}$, (c) $X^\text{te}$ is unavailable during training, and (d) the posterior predictive distribution depends on $P^\text{te}(Z)$, i. e., $\hat{Y} = E_{P^\text{te}(Z)}[f_Z(X)]$.
Vertical Validation: Evaluating Implicit Generative Models for Graphs on Thin Support Regions
There has been a growing excitement that implicit graph generative models could be used to design or discover new molecules for medicine or material design.
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs).
Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study
Automated clinical text anonymization has the potential to unlock the widespread sharing of textual health data for secondary usage while assuring patient privacy and safety.
A Foundation Model for Zero-shot Logical Query Reasoning
Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and logical operations.
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
GraphMETRO employs a Mixture-of-Experts (MoE) architecture with a gating model and multiple expert models, where each expert model targets a specific distributional shift to produce a referential representation w. r. t.
MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
Most MI attacks in the literature take advantage of the fact that ML models are trained to fit the training data well, and thus have very low loss on training instances.
Efficient Subgraph GNNs by Learning Effective Selection Policies
Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs.
A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
The task of inductive link prediction in (discrete) attributed multigraphs infers missing attributed links (relations) between nodes in new test multigraphs.
MetaPhysiCa: OOD Robustness in Physics-informed Machine Learning
A fundamental challenge in physics-informed machine learning (PIML) is the design of robust PIML methods for out-of-distribution (OOD) forecasting tasks.
Causal Lifting and Link Prediction
Existing causal models for link prediction assume an underlying set of inherent node factors -- an innate characteristic defined at the node's birth -- that governs the causal evolution of links in the graph.
Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types
The task of fully inductive link prediction in knowledge graphs has gained significant attention, with various graph neural networks being proposed to address it.
Bias Challenges in Counterfactual Data Augmentation
Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task.
OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs
This work provides the first theoretical study on the ability of graph Message Passing Neural Networks (gMPNNs) -- such as Graph Neural Networks (GNNs) -- to perform inductive out-of-distribution (OOD) link prediction tasks, where deployment (test) graph sizes are larger than training graphs.
Contextual Unsupervised Outlier Detection in Sequences
This work proposes an unsupervised learning framework for trajectory (sequence) outlier detection that combines ranking tests with user sequence models.
Reconstruction for Powerful Graph Representations
Empirically, we show how reconstruction can boost GNN's expressive power -- while maintaining its invariance to permutations of the vertices -- by solving seven graph property tasks not solvable by the original GNN.
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks
Generalizing from observed to new related environments (out-of-distribution) is central to the reliability of classifiers.
Neural Networks for Learning Counterfactual G-Invariances from Single Environments
In order to endow neural networks with the ability to extrapolate over group transformations, we introduce a learning framework counterfactually-guided by the learning hypothesis that any group invariance to (known) transformation groups is mandatory even without evidence, unless the learner deems it inconsistent with the training data.
On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
This work formalizes the associational task of predicting node attribute evolution in temporal graphs from the perspective of learning equivariant representations.
Size-Invariant Graph Representations for Graph Classification Extrapolations
In general, graph representation learning methods assume that the train and test data come from the same distribution.
Neural Network Extrapolations with G-invariances from a Single Environment
In order to endow neural networks with the ability to extrapolate over group transformations, we introduce a learning framework guided by a new learning hypothesis: Any invariance to transformation groups is mandatory even without evidence, unless the learner deems it inconsistent with the training data.
On Single-environment Extrapolations in Graph Classification and Regression Tasks
Extrapolation in graph classification/regression remains an underexplored area of an otherwise rapidly developing field.
Sequential Stratified Regeneration: MCMC for Large State Spaces with an Application to Subgraph Count Estimation
This work considers the general task of estimating the sum of a bounded function over the edges of a graph, given neighborhood query access and where access to the entire network is prohibitively expensive.
Social and Information Networks Data Structures and Algorithms
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in the graph.
Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models
Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in the graph.
Deceptive Deletions for Protecting Withdrawn Posts on Social Platforms
Our mechanism injects decoy deletions, hence creating a two-player minmax game between an adversary that seeks to classify damaging content among the deleted posts and a challenger that employs decoy deletions to masquerade real damaging deletions.
A Collective Learning Framework to Boost GNN Expressiveness
Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels.
Membership Inference Attacks and Defenses in Classification Models
We study the membership inference (MI) attack against classifiers, where the attacker's goal is to determine whether a data instance was used for training the classifier.
Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations
We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics.
Deep Lifetime Clustering
The goal of lifetime clustering is to develop an inductive model that maps subjects into $K$ clusters according to their underlying (unobserved) lifetime distribution.
On the Equivalence between Positional Node Embeddings and Structural Graph Representations
This work provides the first unifying theoretical framework for node (positional) embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks.
Are Graph Neural Networks Miscalibrated?
Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy.
Relational Pooling for Graph Representations
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions.
Ranked #5 on
Drug Discovery
on MUV
Random Spiking and Systematic Evaluation of Defenses Against Adversarial Examples
Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification.
Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
We consider a simple and overarching representation for permutation-invariant functions of sequences (or multiset functions).
Graph Pattern Mining and Learning through User-defined Relations (Extended Version)
In this work we propose R-GPM, a parallel computing framework for graph pattern mining (GPM) through a user-defined subgraph relation.
A Deep Learning Approach for Survival Clustering without End-of-life Signals
The goal of survival clustering is to map subjects (e. g., users in a social network, patients in a medical study) to $K$ clusters ranging from low-risk to high-risk.
Detecting Anomalies in Sequential Data with Higher-order Networks
A major branch of anomaly detection methods relies on dynamic networks: raw sequence data is first converted to a series of networks, then critical change points are identified in the evolving network structure.
Social and Information Networks Physics and Society
From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets
We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC) estimators of Restricted Boltzmann Machines (RBMs).
Stochastic Gradient Descent for Relational Logistic Regression via Partial Network Crawls
Research in statistical relational learning has produced a number of methods for learning relational models from large-scale network data.
Selective Harvesting over Networks
We find that it is possible to collect a much larger set of targets by using multiple classifiers, not by combining their predictions as an ensemble, but switching between classifiers used at each step, as a way to ease the tunnel vision effect.
Bayesian Inference of Online Social Network Statistics via Lightweight Random Walk Crawls
Online social networks (OSN) contain extensive amount of information about the underlying society that is yet to be explored.
Estimating and Sampling Graphs with Multidimensional Random Walks
We show that the proposed sampling method, which we call Frontier sampling, exhibits all of the nice sampling properties of a regular random walk.
Data Structures and Algorithms Networking and Internet Architecture G.3
