Search Results for author:
Found 78 papers, 35 papers with code
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and relevance.
Tractable Transformers for Flexible Conditional Generation
Recent advancements in NAR models, such as diffusion language models, have demonstrated superior performance in unconditional generation compared to AR models (e. g., GPTs) of similar sizes.
Adaptive Width Neural Networks
For almost 70 years, researchers have mostly relied on hyper-parameter tuning to pick the width of neural networks' layers out of many possible choices.
MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning
In this work, we propose a simple transformer-based baseline for multimodal molecular representation learning, integrating three distinct modalities: SMILES strings, 2D graph representations, and 3D conformers of molecules.
LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model
State-of-the-art medical multi-modal large language models (med-MLLM), like LLaVA-Med or BioMedGPT, leverage instruction-following data in pre-training.
Discrete Copula Diffusion
When we apply this approach to autoregressive copula models, the combined model outperforms both models individually in unconditional and conditional text generation.
A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions
In an era where large language models (LLMs) are increasingly integrated into a wide range of everyday applications, research into these models' behavior has surged.
Active Learning for Neural PDE Solvers
While AL is more common in other domains, it has yet to be studied extensively for neural PDE solvers.
Physics-Informed Weakly Supervised Learning for Interatomic Potentials
Our approach improves the accuracy of MLIPs applied to training tasks with sparse training data sets and reduces the need for pre-training computationally demanding models with large data sets.
Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data.
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
Transformer models are increasingly used for solving Partial Differential Equations (PDEs).
Probabilistic Graph Rewiring via Virtual Nodes
Message-passing graph neural networks (MPNNs) have emerged as a powerful paradigm for graph-based machine learning.
Accelerating Transformers with Spectrum-Preserving Token Merging
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e. g., GPT, LLaVa), is an important problem in machine learning.
Learning to Discretize Denoising Diffusion ODEs
We achieve FIDs of 2. 38 (10 NFE), and 2. 27 (10 NFE) on unconditional CIFAR10 and AFHQv2 in 5-10 minutes of training.
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
By learning from high-quality data, machine-learned interatomic potentials achieve accuracy on par with ab initio and first-principles methods at a fraction of their computational cost.
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
Inspired by recent work on using ensembles of conformers in conjunction with 2D graph representations, we propose $\mathrm{E}$(3)-invariant molecular conformer aggregation networks.
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
Long-range interactions are essential for the correct description of complex systems in many scientific fields.
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem.
Image Inpainting via Tractable Steering of Diffusion Models
Further, with the help of an image encoder and decoder, our method can readily accept semantic constraints on specific regions of the image, which opens up the potential for more controlled image generation tasks.
On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging.
Continual Invariant Risk Minimization
Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations.
Probabilistically Rewired Message-Passing Neural Networks
Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input.
Approximate Answering of Graph Queries
We will first provide an overview of the different query types which can be supported by these methods and datasets typically used for evaluation, as well as an insight into their limitations.
Efficient Learning of Discrete-Continuous Computation Graphs
We analyze the behavior of more complex stochastic computations graphs with multiple sequential discrete components.
Learning Disentangled Discrete Representations
Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empirical advantages of discrete latent representations, although the reasons behind their benefits remain unclear.
LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images.
Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning that can tractably answer probabilistic queries.
Learning Neural PDE Solvers with Parameter-Guided Channel Attention
The experiments also show several advantages of CAPE, such as its increased ability to generalize to unseen PDE parameters without large increases inference time and parameter count.
Learning Sparsity of Representations with Discrete Latent Variables
The resulting sparsity of a representation is not fixed, but fits to the observation itself under the pre-defined restriction.
State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
Joint Multilingual Knowledge Graph Completion and Alignment
The proposed model combines two components that jointly accomplish KG completion and alignment.
Ranked #1 on
Knowledge Graph Completion
on DPB-5L (French)
PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
With those metrics we identify tasks which are challenging for recent ML methods and propose these tasks as future challenges for the community.
SIMPLE: A Gradient Estimator for $k$-Subset Sampling
$k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity.
L2XGNN: Learning to Explain Graph Neural Networks
Graph Neural Networks (GNNs) are a popular class of machine learning models.
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
In this work, we present Adaptive IMLE (AIMLE), the first adaptive gradient estimator for complex discrete distributions: it adaptively identifies the target distribution for IMLE by trading off the density of gradient information with the degree of bias in the gradient estimates.
Ordered Subgraph Aggregation Networks
Numerous subgraph-enhanced graph neural networks (GNNs) have emerged recently, provably boosting the expressive power of standard (message-passing) GNNs.
milIE: Modular & Iterative Multilingual Open Information Extraction
In contrast, we explore the hypothesis that it may be beneficial to extract triple slots iteratively: first extract easy slots, followed by the difficult ones by conditioning on the easy slots, and therefore achieve a better overall extraction.
AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark
Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner.
BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation
In this work, we introduce BenchIE: a benchmark and evaluation framework for comprehensive evaluation of OIE systems for English, Chinese, and German.
Ranked #1 on
Open Information Extraction
on BenchIE
VEGN: Variant Effect Prediction with Graph Neural Networks
In contrast, we propose VEGN, which models variant effect prediction using a graph neural network (GNN) that operates on a heterogeneous graph with genes and variants.
Behavioral Testing of Knowledge Graph Embedding Models for Link Prediction
With an extensive set of experiments, we perform and analyze these tests for several KGE models.
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components.
Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
Uncertainty quantification is crucial for building reliable and trustable machine learning systems.
Explaining Neural Matrix Factorization with Gradient Rollback
Moreover, we show theoretically that the difference between gradient rollback's influence approximation and the true influence on a model's behavior is smaller than known bounds on the stability of stochastic gradient descent.
Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders
Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries.
Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas
Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored.
Attending to Future Tokens For Bidirectional Sequence Generation
Treated as a node in a fully connected graph, a placeholder token can take past and future tokens into consideration when generating the actual output token.
Learning Discrete Structures for Graph Neural Networks
With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph.
Ranked #3 on
Node Classification
on Cora: fixed 20 node per class
RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems
Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity and data imbalance and learns transferable latent representations for users, items and their interactions.
MMKG: Multi-Modal Knowledge Graphs
We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs.
State-Regularized Recurrent Neural Networks
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
Learning Representations of Missing Data for Predicting Patient Outcomes
Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches.
Knowledge Graph Completion to Predict Polypharmacy Side Effects
The polypharmacy side effect prediction problem considers cases in which two drugs taken individually do not result in a particular side effect; however, when the two drugs are taken in combination, the side effect manifests.
Towards Transparent Neural Network Acceleration
While the efficiency problem can be partially addressed with specialized hardware and its corresponding proprietary libraries, we believe that neural network acceleration should be transparent to the user and should support all hardware platforms and deep learning libraries.
State-Regularized Recurrent Networks
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
Learning Sequence Encoders for Temporal Knowledge Graph Completion
In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations.
LRMM: Learning to Recommend with Missing Modalities
More importantly, LRMM is more robust to previous methods in alleviating data-sparsity and the cold-start problem.
A Comparative Study of Distributional and Symbolic Paradigms for Relational Learning
Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs.
Contextual Hourglass Networks for Segmentation and Density Estimation
These shortcut connections improve the performance and it is hypothesized that this is due to mitigating effects on the vanishing gradient problem and the ability of the model to combine feature maps from earlier and later layers.
Learning Short-Cut Connections for Object Counting
Standard short-cut connections are connections between layers in deep neural networks which skip at least one intermediate layer.
Towards a Spectrum of Graph Convolutional Networks
We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies.
BrainSlug: Transparent Acceleration of Deep Learning Through Depth-First Parallelism
Neural network frameworks such as PyTorch and TensorFlow are the workhorses of numerous machine learning applications ranging from object recognition to machine translation.
Representation Learning for Resource Usage Prediction
Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem.
TransRev: Modeling Reviews as Translations from Users to Items
This is exploited in sentiment analysis where machine learning models are used to predict the review score from the text of the review.
Learning Graph Representations with Embedding Propagation
We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data.
KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features.
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs
A visual-relational knowledge graph (KG) is a multi-relational graph whose entities are associated with images.
Net2Vec: Deep Learning for the Network
We present Net2Vec, a flexible high-performance platform that allows the execution of deep learning algorithms in the communication network.
Discriminative Gaifman Models
We present discriminative Gaifman models, a novel family of relational machine learning models.
Ranked #28 on
Link Prediction
on WN18
Learning Convolutional Neural Networks for Graphs
Numerous important problems can be framed as learning from graph data.
Ranked #3 on
Graph Classification
on COX2
Lifted Probabilistic Inference for Asymmetric Graphical Models
Lifted probabilistic inference algorithms have been successfully applied to a large number of symmetric graphical models.
Markov Chains on Orbits of Permutation Groups
Thus, we present the first lifted MCMC algorithm for probabilistic graphical models.
On the Conditional Independence Implication Problem: A Lattice-Theoretic Approach
A lattice-theoretic framework is introduced that permits the study of the conditional independence (CI) implication problem relative to the class of discrete probability measures.
Exchangeable Variable Models
A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations.
Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference
We develop a theory of finite exchangeability and its relation to tractable probabilistic inference.
RockIt: Exploiting Parallelism and Symmetry for MAP Inference in Statistical Relational Models
RockIt is a maximum a-posteriori (MAP) query engine for statistical relational models.
Symmetry-Aware Marginal Density Estimation
The Rao-Blackwell theorem is utilized to analyze and improve the scalability of inference in large probabilistic models that exhibit symmetries.
