Michael Kampffmeyer, Sigurd Løkse, Robert Jenssen, Daniel Trosten
We lifted 12 functions out of this paper's own repositories and ran 11 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.
| Repository | Role | Ran |
|---|---|---|
| DanielTrosten/DeepMVC | canonical | 11 of 12 |
| Function | Status | Where it lives |
|---|---|---|
| cdist | Ran | DanielTrosten/DeepMVC/src/lib/kernel.py code served (permissive licence) · get_code("0bedbd9344d129bf") |
| cmat_from_dict | Ran | DanielTrosten/DeepMVC/src/lib/metrics.py code served (permissive licence) · get_code("d37a39e10c3dab6d") |
| cmat_to_dict | Ran | DanielTrosten/DeepMVC/src/lib/metrics.py code served (permissive licence) · get_code("ae2a5def5271209b") |
| ensure_iterable | Ran | DanielTrosten/DeepMVC/src/helpers.py code served (permissive licence) · get_code("f592159079896a8c") |
| get_normalizer | Ran | DanielTrosten/DeepMVC/src/lib/normalization.py code served (permissive licence) · get_code("6507fdcc7239a027") |
| kernel_from_distance_matrix | Ran | DanielTrosten/DeepMVC/src/lib/kernel.py code served (permissive licence) · get_code("5bb1cc362256db4d") |
| ordered_cmat | Ran | DanielTrosten/DeepMVC/src/lib/metrics.py code served (permissive licence) · get_code("6904d3f9489d3c4f") |
| register_loss_term | Ran | DanielTrosten/DeepMVC/src/register.py code served (permissive licence) · get_code("055b11da844a8f7f") |
| register_model | Ran | DanielTrosten/DeepMVC/src/register.py code served (permissive licence) · get_code("53e699a04f764af0") |
| str2bool | Ran | DanielTrosten/DeepMVC/src/helpers.py code served (permissive licence) · get_code("7c508037b40522af") |
| vector_kernel | Ran | DanielTrosten/DeepMVC/src/lib/kernel.py code served (permissive licence) · get_code("e4d4f68bd4cc242c") |
| npy | Not yet run | DanielTrosten/DeepMVC/src/helpers.py code served (permissive licence) · get_code("8b89b0976ceefec8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of selfsupervision-based methods for deep MVC, potentially slowing the progress of the field. To address this, we present Deep-MVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to make key observations about the effect of self-supervision, and in particular, drawbacks of aligning representations with contrastive learning. Further, we prove that contrastive alignment can negatively influence cluster separability, and that this effect becomes worse when the number of views increases. Motivated by our findings, we develop several new DeepMVC instances with new forms of self-supervision. We conduct extensive experiments and find that (i) in line with our theoretical findings, contrastive alignments decreases performance on datasets with many views; (ii) all methods benefit from some form of self-supervision; and (iii) our new instances outperform previous methods on several datasets. Based on our results, we suggest several promising directions for future research. To enhance the openness of the field, we provide an open-source implementation of Deep-MVC, including recent models and our new instances. Our implementation includes a consistent evaluation protocol, facilitating fair and accurate evaluation of methods and components 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.09877")
get_code_for_paper("2303.09877")
have("2303.09877")
Connect an agent — have() is free.