Representation Learning

Zipfian Whitening: Weighting PCA whitening by word frequency dramatically improves NLP task performance, surpassing established baselines and providing a theoretical framework for existing methods.

This paper introduces a novel, task-agnostic method for ranking embedding models using information sufficiency, a concept derived from communication theory and statistical experiments comparison, demo…

Aligning vision models to human perceptual similarity judgments significantly boosts performance in diverse vision tasks like counting and segmentation, but surprisingly reduces performance in natural…

High-resolution datasets with diverse classes significantly improve the transferability of pretrained DNNs by reducing representation compression and mitigating the ’tunnel effect.'

Tri-Hom disentangles graph homophily into label, structural, and feature aspects, providing a more comprehensive and accurate metric for predicting GNN performance.

Using tropical geometry, researchers reveal that ReLU-activated message-passing GNNs learn continuous piecewise linear functions, highlighting their expressivity limits and paving the way for enhanced…

This paper introduces r-lWL, a new graph isomorphism test hierarchy that surpasses the limitations of the Weisfeiler-Leman test by counting cycles up to length r+2, and its GNN counterpart, r-lMPNN, w…

This paper proves that Čech persistence diagrams converge to the true underlying shape precisely when using Wasserstein distances with p > m, where m is the submanifold dimension, significantly advanc…

This paper bridges the gap between synthetic and real image disentanglement by proposing a novel transfer learning approach. The method leverages weakly supervised learning on synthetic data to train…

Boosting hippocampal spatial resolution surprisingly shrinks its contextual memory capacity, revealing a crucial trade-off between precision and context storage.

ATProt: Adversarial training makes protein interface prediction robust to flexibility!

Neural circuits for goal-directed navigation are modeled as Lie group operator searches, implemented by a two-layer feedforward circuit mimicking Drosophila’s navigation system.

Ada-ReAlign: a novel algorithm for continual test-time adaptation that leverages non-stationary representation learning to effectively align unlabeled data streams with source data, enhancing model ad…

Temp-G³NTK: a novel temporal graph neural tangent kernel guarantees convergence to graphon NTK, offering superior performance in temporal graph classification and node-level tasks.

SubgDiff enhances molecular representation learning by incorporating substructural information into a diffusion model framework, achieving superior performance in molecular force predictions.

Neuromodulated RNNs (NM-RNNs) enhance RNN flexibility by dynamically scaling recurrent weights using a neuromodulatory subnetwork, achieving higher accuracy and generalizability on various tasks compa…

Spectral graph pruning simultaneously mitigates over-squashing and over-smoothing in GNNs via edge deletion, improving generalization.

Soft Tensor Product Representations (Soft TPRs) revolutionize compositional visual representation learning by seamlessly blending continuous vector spaces and compositional structures, leading to supe…

TS-LDDMM: Unsupervised time-series analysis handles irregular data, offering interpretable shape-based representations & exceeding existing methods in benchmarks.

Sequential Signal Mixing Aggregation (SSMA) boosts message-passing graph neural network performance by effectively mixing neighbor features, achieving state-of-the-art results across various benchmark…