Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

• URL: http://arxiv.org/abs/2210.02149v1
• Date: Wed, 5 Oct 2022 11:08:04 GMT
• Title: Relational Proxies: Emergent Relationships as Fine-Grained Discriminators
• Authors: Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata, Anjan Dutta
• Abstract summary: We propose a novel approach that leverages information between the global and local part of an object for encoding its label. We design Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets. We also experimentally validate our theory and obtain consistent results across multiple benchmarks.
• Score: 52.17542855760418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to the overall global structure of the object. We propose Relational Proxies, a novel approach that leverages the relational information between the global and local views of an object for encoding its semantic label. Starting with a rigorous formalization of the notion of distinguishability between fine-grained categories, we prove the necessary and sufficient conditions that a model must satisfy in order to learn the underlying decision boundaries in the fine-grained setting. We design Relational Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets and achieve state-of-the-art results on all of them, surpassing the performance of all existing works with a margin exceeding 4% in some cases. We also experimentally validate our theory on fine-grained distinguishability and obtain consistent results across multiple benchmarks. Implementation is available at https://github.com/abhrac/relational-proxies.

Related papers

• Multi-Relation Extraction in Entity Pairs using Global Context [0.8437187555622164]
  This paper introduces a novel input embedding approach to capture the positions of mentioned entities throughout a document.<n>The performance of the proposed method has been tested on three benchmark relation extraction datasets.<n>Theoretically, it advances global context modeling and multi-sentence reasoning in document-level relation extraction.
  arXiv  Detail & Related papers  (2025-07-23T13:24:32Z)
• Causal LLM Routing: End-to-End Regret Minimization from Observational Data [3.3580884064577616]
  LLM routing aims to select the most appropriate model for each query.<n>Prior approaches typically adopt a decoupled strategy, where the metrics are first predicted and the model is then selected based on these estimates.<n>We propose a causal end-to-end framework that learns routing policies by minimizing decision-making regret from observational data.
  arXiv  Detail & Related papers  (2025-05-21T21:34:18Z)
• Enforcing Fairness Where It Matters: An Approach Based on Difference-of-Convex Constraints [12.054667230143803]
  We focus on achieving full fairness across all score ranges by predictive models, ensuring in both high and low-scoring populations.<n>We propose a novel score of interest as the middle where decisions are most contested, while maintaining flexibility in other regions.<n>We introduce two statistical metrics to rigorously evaluate fairness within a given score range.
  arXiv  Detail & Related papers  (2025-05-18T19:50:01Z)
• FedSaaS: Class-Consistency Federated Semantic Segmentation via Global Prototype Supervision and Local Adversarial Harmonization [14.90727017126931]
  Federated semantic segmentation enables pixel-level classification in images through collaborative learning.<n>We propose a novel framework that strikes class consistency, termed FedSaaS.<n>Our framework significantly improves average segmentation accuracy and effectively addresses the class-consistency representation problem.
  arXiv  Detail & Related papers  (2025-05-14T13:38:30Z)
• Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithm [14.980926991441345]
  We show that datasets containing interventional data can be effectively extracted under realistic assumptions about the data distribution. We introduce interventional faithfulness, which relies on comparisons between the marginal distributions of each variable across observational and interventional settings. We also introduce Intersort, an algorithm designed to infer the causal order from datasets containing large numbers of single-variable interventions.
  arXiv  Detail & Related papers  (2024-05-28T16:07:17Z)
• Causally Inspired Regularization Enables Domain General Representations [14.036422506623383]
  Given a causal graph representing the data-generating process shared across different domains/distributions, enforcing sufficient graph-implied conditional independencies can identify domain-general (non-spurious) feature representations. We propose a novel framework with regularizations, which we demonstrate are sufficient for identifying domain-general feature representations without a priori knowledge (or proxies) of the spurious features. Our proposed method is effective for both (semi) synthetic and real-world data, outperforming other state-of-the-art methods in average and worst-domain transfer accuracy.
  arXiv  Detail & Related papers  (2024-04-25T01:33:55Z)
• Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning [60.058083574671834]
  This paper presents a novel FCCL+, federated correlation and similarity learning with non-target distillation. For heterogeneous issue, we leverage irrelevant unlabeled public data for communication. For catastrophic forgetting in local updating stage, FCCL+ introduces Federated Non Target Distillation.
  arXiv  Detail & Related papers  (2023-09-28T09:32:27Z)
• Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics [80.07271410743806]
  We study the relationship between cross-domain learning (CD) and model fairness. We introduce a benchmark on face and medical images spanning several demographic groups as well as classification and localization tasks. Our study covers 14 CD approaches alongside three state-of-the-art fairness algorithms and shows how the former can outperform the latter.
  arXiv  Detail & Related papers  (2023-03-25T09:34:05Z)
• Repairing Regressors for Fair Binary Classification at Any Decision Threshold [8.322348511450366]
  We show that we can increase fair performance across all thresholds at once. We introduce a formal measure of Distributional Parity, which captures the degree of similarity in the distributions of classifications for different protected groups. Our main result is to put forward a novel post-processing algorithm based on optimal transport, which provably maximizes Distributional Parity.
  arXiv  Detail & Related papers  (2022-03-14T20:53:35Z)
• Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set [50.67431815647126]
  Post-hoc global/local feature attribution methods are being progressively employed to understand machine learning models. We show that partial orders of local/global feature importance arise from this methodology. We show that every relation among features present in these partial orders also holds in the rankings provided by existing approaches.
  arXiv  Detail & Related papers  (2021-10-26T02:53:14Z)
• MultiFair: Multi-Group Fairness in Machine Learning [52.24956510371455]
  We study multi-group fairness in machine learning (MultiFair) We propose a generic end-to-end algorithmic framework to solve it. Our proposed framework is generalizable to many different settings.
  arXiv  Detail & Related papers  (2021-05-24T02:30:22Z)
• Reinforcement Learning based Collective Entity Alignment with Adaptive Features [35.04861875266298]
  We propose a reinforcement learning (RL) based model to align entities collectively. Under the RL framework, we devise the coherence and exclusiveness constraints to characterize the interdependence and collective alignment. Our proposal is evaluated on both cross-lingual and mono-lingual EA benchmarks and compared against state-of-the-art solutions.
  arXiv  Detail & Related papers  (2021-01-05T05:04:09Z)
• Domain Adaptative Causality Encoder [52.779274858332656]
  We leverage the characteristics of dependency trees and adversarial learning to address the tasks of adaptive causality identification and localisation. We present a new causality dataset, namely MedCaus, which integrates all types of causality in the text.
  arXiv  Detail & Related papers  (2020-11-27T04:14:55Z)
• Towards Context-Agnostic Learning Using Synthetic Data [5.892876463573452]
  We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias and an error term, and exhibits a surprisingly weak dependence on the true labels. Inspired by these results, we present an algorithm aimed at minimizing the bias term by exploiting the ability to sample from each set independently.
  arXiv  Detail & Related papers  (2020-05-29T17:53:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.