REVIEW 8 cited by
Ranking via Sinkhorn Propagation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular metrics such as precision and discounted cumulative gain. In particular, we observe that expectations of these gains are completely characterized by the marginals of the corresponding distribution over permutation matrices. Thus, the expectations of rank-linear objectives can always be described through locations in the Birkhoff polytope, i.e., doubly-stochastic matrices (DSMs). We propose a technique for learning DSM-based ranking functions using an iterative projection operator known as Sinkhorn normalization. Gradients of this operator can be computed via backpropagation, resulting in an algorithm we call Sinkhorn propagation, or SinkProp. This approach can be combined with a wide range of gradient-based approaches to rank learning. We demonstrate the utility of SinkProp on several information retrieval data sets.
Forward citations
Cited by 8 Pith papers
-
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Hypergraph neural networks obey a strict expressivity hierarchy indexed by hypertree width, creating a Width Wall that no fixed-depth model, hidden dimension, or training procedure can cross for wider patterns.
-
SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery
SVI-DAG couples normalizing flows over edge logits with stein variational gradient descent on node orderings to learn multimodal Bayesian posteriors over DAGs.
-
Learning Permutation from Structure Without Supervision
Entropy-adaptive Gumbel-Sinkhorn formulation for unsupervised permutation learning that modulates temperature per assignment to address non-uniform uncertainty.
-
SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
SOTAlign aligns frozen vision and language encoders with 10k pairs plus up to 1M unpaired samples, beating supervised baselines by 5-10 points on COCO retrieval and ImageNet classification.
-
Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach
A topology-adaptive deformation model that edits a template's topology during ARAP alignment achieves better Chamfer distance on meshes with topological artifacts than trained shape-matching baselines, at the cost of ...
-
SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
Spectral band permutation pretraining with curriculum learning reaches R2=0.9456 for EnMAP soil organic carbon estimation, beating the tested SSL and supervised baselines.
-
Stream-aware Side Adaptation for Large Pre-trained Multimodal Embedding Models in Sequential Recommendation
Stream-aware fusion (SHAF) and residual stream adapters (ReSA) stabilize deep side adaptation of frozen multimodal embedding models and improve sequential recommendation over standard side adapters.
-
GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
GMN4AD applies graph matching and test-time contrastive adaptation to improve Alzheimer's diagnosis accuracy on heterogeneous multi-center sMRI datasets.
Discussion (0). Continue with ORCID to comment.