← Back to all news
arXiv Machine Learning

Certified Topological Interaction in Neural Representations: Class Disentanglement Is Mostly Pairwise

Related stories

arXiv Machine Learning
Sep 21

Certified Topological Interaction in Neural Representations: Exact Tests and the Statistic They Require

The paper introduces the Intersection Euler Characteristic Profile, a topological metric for measuring class overlap in neural representations, and provides exact permutation and sign‑flip tests to assess disentanglement across layers. Using this statistic, the authors analyze 111 networks and 52,650 measurements, finding that disentanglement is depth‑graded, occurs early, and is influenced by training choices such as augmentation and weight decay. The study also demonstrates that the unnormalized mass of the profile predicts test accuracy, while the dimensionless quotient does not outperform simple linear probes.

By Sushovan Majhi
llms
More like this →
arXiv Machine Learning
Jul 8

Geometric Stability: The Missing Axis of Representations

arXiv:2601. 09173v5 Announce Type: replace Abstract: Representational similarity analysis and related methods compare the internal geometries of neural networks, but they measure only alignment between spaces, leaving a blind spot -- whether a representation's structure is reliably recoverable, not merely similar.

By Prashant C. Raju
safety
More like this →
arXiv AI
3d ago

Unmerge: Efficient Machine Unlearning via Task Arithmetic

The paper introduces Unmerge, an efficient machine unlearning algorithm that treats unlearning as the inverse of task arithmetic. By representing the forget component as a low‑rank basis at each layer, Unmerge optimizes three goals—matching the merged vector, suppressing leakage, and bounding correction size—to limit forget leakage and retain damage. Experiments on ResNet‑50, ViT‑S/16, and Llama‑3.2‑3B show significant performance gains over existing methods while maintaining privacy and feature‑distribution fidelity.

By Haoran Tang, Andrew Tan, Rajiv Khanna
llmsfine-tuning
More like this →
arXiv AI
4d ago

Representable but Unlearned: Encoding Rank and the Interaction-Prediction Floor

The paper investigates how input encodings constrain the set of contrasts a predictor can reproduce, even when no individual contrast is forced to zero. By computing the attainable contrast space from an encoder’s equivalence classes and a fixed contrast design—without using labels, loss, or a fitted model—the authors derive an empirical error floor for any unrestricted decoder on those classes. Experiments on a 140‑rectangle siRNA interaction panel show that a graph neural network’s training‑only feature mask reduces the rank of interaction contrasts from 140 to 72, creating a floor of 0.009980 (14.6% of the fitted model’s interaction squared error). Removing the mask eliminates the floor but only marginally improves MSE, while restoring chemistry columns recovers full rank. A separate RNA‑splicing predictor with an injective encoding achieves full rank and a zero floor, illustrating that the encoding itself, not the model, limits recoverable contrast space.

By Zahra Khodagholi, Niloofar Yousefi
More like this →