arXiv:2605. 13894v2 Announce Type: replace-cross Abstract: In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus operators, inducing a piecewise-linear structure aligned with dynamic programming formulations.
By Chris Teska, Kurt Pasque, Ruriko Yoshida, Baran Hashemi
The study investigates whether self‑supervised pretraining improves molecular graph neural networks by adapting the LeJEPA architecture to molecular graphs. While pretraining enhances learned representations and a frozen probe outperforms random initialization on tasks such as ogbg‑molhiv, it does not consistently boost finetuning performance across different data splits. Combining pretrained embeddings with 1024‑bit Morgan fingerprints yields modest gains, indicating that pretraining provides complementary information best exploited at the feature level.
By Micha{\l} Kulczykowski, Rafa{\l} {\L}ab\k{e}dzki
arXiv:2603. 06952v2 Announce Type: replace Abstract: As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods.
By Yuhang Song, Naima Abrar Shami, Romaric Duvignau, Vasiliki Kalavri
arXiv:2310.08774v3 Announce Type: replace-cross
Abstract: Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history an...
By Mingyang Zhou, Zichao Yan, Elliot Layne, Esmeralda S. Whitammer, Dinghuai Zhang, Moksh Jain, Mathieu Blanchette, Yoshua Bengio
arXiv:2607. 19376v1 Announce Type: cross Abstract: Machine learning models trained on biochemical data are routinely evaluated using splits that fail to account for relational structure, causing information leakage and over-optimistic performance estimates.
By Anthony Lavertu, Jacob Cote, Jacques Corbeil, Sophie Gobeil, Pascal Germain
Hyperparameter optimization (HPO) for Random Forest faces a specific difficulty in tuning the number of trees: the predictive score typically improves monotonically with ensemble size, so standard methods such as Tree-structured Parzen Estimator (TPE) and Hyperband require a predefined search range and often drive the estimate toward its right boundary. Early-stopping strategies avoid fixing such a range, but can be sensitive to score noise and prone to premature stopping.