Search Results for author: Sammy Khalife

Found 6 papers, 0 papers with code

Sequence graphs realizations and ambiguity in language models

no code implementations13 Feb 2024 Sammy Khalife, Yann Ponty, Laurent Bulteau

For a window of size at least 3, we prove hardness of all variants, even when w is considered as a constant, with the notable exception of the undirected/unweighted case for which we propose an XP algorithms for both (realizability and enumeration) problems, tight due to a corresponding W[1]-hardness result.

Data-driven algorithm design using neural networks with applications to branch-and-cut

no code implementations4 Feb 2024 Hongyu Cheng, Sammy Khalife, Barbara Fiedorowicz, Amitabh Basu

We build upon recent work in this line of research by introducing the idea where, instead of selecting a single algorithm that has the best performance, we allow the possibility of selecting an algorithm based on the instance to be solved.

Graph Neural Networks with polynomial activations have limited expressivity

no code implementations19 Oct 2023 Sammy Khalife

The expressivity of Graph Neural Networks (GNNs) can be entirely characterized by appropriate fragments of the first order logic.

On the power of graph neural networks and the role of the activation function

no code implementations10 Jul 2023 Sammy Khalife, Amitabh Basu

In contrast, it was already known that unbounded GNNs (those whose size is allowed to change with the graph sizes) with piecewise polynomial activations can distinguish these vertices in only two iterations.

Neural networks with linear threshold activations: structure and algorithms

no code implementations15 Nov 2021 Sammy Khalife, Hongyu Cheng, Amitabh Basu

We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are necessary and sufficient to represent any function representable in the class.

Cannot find the paper you are looking for? You can Submit a new open access paper.