Search Results for author:
Found 19 papers, 9 papers with code
Does the Performance of Text-to-Image Retrieval Models Generalize Beyond Captions-as-a-Query?
ConQA comprises 30 descriptive and 50 conceptual queries on 43k images with more than 100 manually annotated images per query.
Ranked #1 on
Image Retrieval
on ConQA Conceptual
Benchmarking Large Language Models for Molecule Prediction Tasks
Our investigation reveals several key insights: Firstly, LLMs generally lag behind ML models in achieving competitive performance on molecule tasks, particularly when compared to models adept at capturing the geometric structure of molecules, highlighting the constrained ability of LLMs to comprehend graph data.
EvolMPNN: Predicting Mutational Effect on Homologous Proteins by Evolution Encoding
Predicting protein properties is paramount for biological and medical advancements.
Harnessing Large Language Models as Post-hoc Correctors
We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model.
Autonomous microARPES
Angle-resolved photoemission spectroscopy (ARPES) is a technique used to map the occupied electronic structure of solids.
On the Robustness of Post-hoc GNN Explainers to Label Noise
Proposed as a solution to the inherent black-box limitations of graph neural networks (GNNs), post-hoc GNN explainers aim to provide precise and insightful explanations of the behaviours exhibited by trained GNNs.
How Faithful are Self-Explainable GNNs?
Self-explainable deep neural networks are a recent class of models that can output ante-hoc local explanations that are faithful to the model's reasoning, and as such represent a step forward toward filling the gap between expressiveness and interpretability.
ActUp: Analyzing and Consolidating tSNE and UMAP
tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings.
Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey from Precision to Interpretability
The integration of Artificial Intelligence (AI) into the field of drug discovery has been a growing area of interdisciplinary scientific research.
GiDR-DUN; Gradient Dimensionality Reduction -- Differences and Unification
In this work, we show that this is indeed possible by combining the two approaches into a single method.
GRASP: Graph Alignment through Spectral Signatures
In this paper, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs.
SOFOS: Demonstrating the Challenges of Materialized View Selection on Knowledge Graphs
Although popular in relational databases, view materialization for RDF and SPARQL has not yet transitioned into practice, due to the non-trivial application to the RDF graph model.
Knowledge Graphs
Databases
Bandits for Learning to Explain from Explanations
We introduce Explearn, an online algorithm that learns to jointly output predictions and explanations for those predictions.
What if Neural Networks had SVDs?
We present an algorithm that is fast enough to speed up several matrix operations.
FREDE: Anytime Graph Embeddings
Low-dimensional representations, or embeddings, of a graph's nodes facilitate several practical data science and data engineering tasks.
The Shape of Data: Intrinsic Distance for Data Distributions
The ability to represent and compare machine learning models is crucial in order to quantify subtle model changes, evaluate generative models, and gather insights on neural network architectures.
SGR: Self-Supervised Spectral Graph Representation Learning
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand.
NetLSD: Hearing the Shape of a Graph
However, it is a hard task in terms of the expressiveness of the employed similarity measure and the efficiency of its computation.
Social and Information Networks
VERSE: Versatile Graph Embeddings from Similarity Measures
Embedding a web-scale information network into a low-dimensional vector space facilitates tasks such as link prediction, classification, and visualization.
