SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02392 · ICLR · 2025

MANTRA: The Manifold Triangulations Assemblage

Bastian Rieck, Sergio Escalera, Rubén Ballester, Ernst Röell, Daniel Schmid, Mathieu Alain, Carles Casacuberta

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 18 functions out of this paper's own repositories and ran 18 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
aidos-lab/MANTRA canonical 10 of 10
aidos-lab/mantra-benchmarks canonical 8 of 8
FunctionStatusWhere it lives
area Ran aidos-lab/MANTRA/mantra/realize_2d_triangulation.py
code served (permissive licence) · get_code("805fba6734cde521")
areas Ran aidos-lab/MANTRA/mantra/realize_2d_triangulation.py
code served (permissive licence) · get_code("f862c5fbf34cb27d")
betti_loss_fn Ran aidos-lab/mantra-benchmarks/code/metrics/loss.py
code served (permissive licence) · get_code("12cf54a9d20dfb7d")
compute_ecc Ran aidos-lab/mantra-benchmarks/code/models/DECT.py
code served (permissive licence) · get_code("f06cf1e29cc594b4")
compute_ect_points Ran aidos-lab/mantra-benchmarks/code/models/DECT.py
code served (permissive licence) · get_code("c0bc0a11ee2e67a8")
dict_of_tensors_to_device Ran aidos-lab/mantra-benchmarks/code/general_utils.py
code served (permissive licence) · get_code("bb3b77f6de0c2873")
filter_by_class_count Ran aidos-lab/MANTRA/mantra/datasets/utils.py
code served (permissive licence) · get_code("541ed72301e38e39")
generate_uniform_directions Ran aidos-lab/mantra-benchmarks/code/models/DECT.py
code served (permissive licence) · get_code("591921e053a5befe")
get_identifiers Ran aidos-lab/MANTRA/mantra/set_property.py
code served (permissive licence) · get_code("a00bec06ffcaf1f3")
intersects Ran aidos-lab/MANTRA/mantra/realize_2d_triangulation.py
code served (permissive licence) · get_code("d000ee40d5aa3e00")
list_of_tensors_to_device Ran aidos-lab/mantra-benchmarks/code/general_utils.py
code served (permissive licence) · get_code("aeea8c085594c46e")
make_split_index Ran aidos-lab/MANTRA/mantra/datasets/utils.py
code served (permissive licence) · get_code("42ed20d520be082e")
maybe_coerce Ran aidos-lab/MANTRA/mantra/set_property.py
code served (permissive licence) · get_code("caa0e7b4efbe40f2")
name_loss_fn Ran aidos-lab/mantra-benchmarks/code/metrics/loss.py
code served (permissive licence) · get_code("a698b4bddb714dde")
orientability_loss_fn Ran aidos-lab/mantra-benchmarks/code/metrics/loss.py
code served (permissive licence) · get_code("47bc01961976fe6a")
parse_homology_groups Ran aidos-lab/MANTRA/mantra/lex_to_json.py
code served (permissive licence) · get_code("6ee83d7e91140a1f")
parse_topological_type Ran aidos-lab/MANTRA/mantra/lex_to_json.py
code served (permissive licence) · get_code("4feac675da3df35b")
process_triangulation Ran aidos-lab/MANTRA/mantra/lex_to_json.py
code served (permissive licence) · get_code("122b0829c12375b3")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The rising interest in leveraging higher-order interactions present in complex systems has led to a surge in more expressive models exploiting higher-order structures in the data, especially in topological deep learning (TDL), which designs neural networks on higherorder domains such as simplicial complexes. However, progress in this field is hindered by the scarcity of datasets for benchmarking these architectures. To address this gap, we introduce MANTRA, the first large-scale, diverse, and intrinsically higher-order dataset for benchmarking higher-order models, comprising over 43,000 and 250,000 triangulations of surfaces and three-dimensional manifolds, respectively. With MANTRA, we assess several graph-and simplicial complex-based models on three topological classification tasks. We demonstrate that while simplicial complex-based neural networks generally outperform their graph-based counterparts in capturing simple topological invariants, they also struggle, suggesting a rethink of TDL. Thus, MANTRA serves as a benchmark for assessing and advancing topological methods, leading the way for more effective higher-order models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.02392")
get_code_for_paper("2410.02392")
have("2410.02392")

Connect an agent — have() is free.