2 citations · 4 across the 11 of their papers we have counts for
10 papers · 1 filter
Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines
Irena Girshovitz, Dan Zeltzer, Ran Gilad-Bachrach
While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on i…
Graph Mixing Additive Networks
Maya Bechler-Speicher, Andrea Zerio, Maor Huri +5
We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN repre…
A Generative Approach for Semantic Auditing of Electronic Health Records
Irena Girshovitz, Atai Ambus, Moni Shahar +1
The reliability of clinical artificial intelligence (AI) depends on high-quality data, yet Electronic Health Records are often inconsistent with existing scientific knowledge. Curr…
SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Maya Bechler-Speicher, Andrea Zerio, Maor Huri +5
Real-world temporal data often consists of multiple signal types recorded at irregular, asynchronous intervals. For instance, in the medical domain, different types of blood tests…
Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers
Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher +3
Transformers have revolutionized the field of machine learning. In particular, they can be used to solve complex algorithmic problems, including graph-based tasks. In such algorith…
Towards Invariance to Node Identifiers in Graph Neural Networks
Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schonlieb +2
Message-Passing Graph Neural Networks (GNNs) are known to have limited expressive power, due to their message passing structure. One mechanism for circumventing this limitation is…
On the Utilization of Unique Node Identifiers in Graph Neural Networks
Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schönlieb +2
Graph Neural Networks have inherent representational limitations due to their message-passing structure. Recent work has suggested that these limitations can be overcome by using u…
The Interpretable and Effective Graph Neural Additive Networks
Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc e…
Tighter Bounds on the Information Bottleneck with Application to Deep Learning
Nir Weingarten, Zohar Yakhini, Moshe Butman +1
Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts…
Graph Neural Networks Use Graphs When They Shouldn't
Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach +1
Predictions over graphs play a crucial role in various domains, including social networks and medicine. Graph Neural Networks (GNNs) have emerged as the dominant approach for learn…