Neural Networks最新文献

The tensor-based multi-view clustering approach captures the high-order correlation among different views by learning a low-rank representation tensor, which has achieved favorable performance in multi-view clustering. However, the tensor rank approximation functions used by the extant algorithms are not tight enough to the true rank of the tensor, leading to the undesired low-rank structure. Besides, the fusion strategy at the affinity matrix level is less robust to noise, resulting in sub-optimal clustering results. To tackle these issues, we propose a Partition-Level Fusion Induced Multi-view Subspace Clustering with Tensorial Geman Rank (PFMSC-TGR). Firstly, a tighter surrogate of tensor rank is designed, named Tensorial Geman Rank (TGR). Under the constraint of TGR, all non-zero singular values are penalized with suitable strength, leading to a strongly discriminative representation tensor. Secondly, we fuse the information of all views at the partition level to obtain a consistent indicator matrix, which enhances the stability of the model against noisy information. Furthermore, we combine these two items in a unified framework and employ an efficient algorithm to optimize the objective function. We further mathematically prove that the sequences constructed by our proposed algorithm converge to the stationary KKT point. Extensive experiments are conducted on nine data sets with different types and sizes, and the results of comparison with the eleven state-of-the-art algorithms prove the superiority of our algorithm. Our code is publicly available at: https://github.com/jijintian/PFMSC-TGR.

Pairwise comparison classification (Pcomp) is a recently thriving weakly-supervised method that generates a binary classifier based on feedback information from comparisons between unlabeled data pairs (one is more likely to be positive than the other). However, this approach turns out challenging in more complex scenarios involving comparisons among more than two instances. To overcome this problem, this paper starts with a comprehensive exploration of the triplet comparisons data (the first instance is more likely to be positive than the second instance, and the second instance is more likely to be positive than the third instance). Then the problem is extended to investigate N-Tuple comparisons learning (NT-Comp: the confidence of belonging to the positive class from the first instance to the last instance is in descending order, with the first instance being the biggest). This generalized model accommodates not only pairwise comparisons data but also more than two comparisons data. This paper derives an unbiased risk estimator for N-Tuple comparisons learning. The estimation error bound is also established theoretically. Finally, an experiment is conducted to validate the effectiveness of the proposed method.

Existing group fairness-aware training methods fall into two categories: re-weighting underrepresented groups according to certain rules, or using regularization terms such as smoothed approximations of fairness metrics or surrogate statistical quantities. While each category has its own strength in applicability or performance when compared to each other, their successful performances are typically limited to specific cases. To that end, we propose a new approach called FairDRO, which takes advantage of both categories through a classwise group distributionally robust optimization (DRO) framework. Our method unifies re-weighting and regularization by incorporating a well-justified group fairness metric into the objective as regularization, but solving it through a principled re-weighting strategy. To optimize our resulting objective efficiently, we adopt an iterative algorithm and consequently develop two variants of FairDRO algorithm depending on the choice of surrogate loss. For in-depth understanding, we derive three theoretical results: (i) a closed-form solution for the correct re-weights; (ii) justifications for using the surrogate losses; and (iii) a convergence analysis of our method. Experimental results show that our algorithms consistently achieve state-of-the-art performance in accuracy-fairness trade-offs across multiple benchmarks, demonstrating scalability and broad applicability compared to existing methods.

In hierarchical reinforcement learning, unsupervised skill discovery holds promise for overcoming the challenge of sparse rewards commonly encountered in traditional reinforcement learning. Although previous unsupervised skill discovery methods excelled at maximizing intrinsic rewards, they often overly prioritized skill diversity. Unrestrained pursuit of diversity leads skills to concentrate attention on unexplored domains, overlooking the internal consistency of skills themselves, resulting in the state visit distribution of individual skills lacking concentration. To address this problem, the Constrained Skill Discovery (CoSD) algorithm is proposed to balance the diversity and behavioral consistency of skills. CoSD integrates both the forward and the reverse decomposition forms of mutual information and uses the maximum entropy policy to maximize the information-theoretic objective of skill learning while requiring that each skill maintain low state entropy internally, which enhances the behavioral consistency of the skills while pursuing the diversity of the skills and ensures that the learned skills have a high degree of stability. Experimental results demonstrated that, compared with other skill discovery methods based on mutual information, skills from CoSD exhibited a more concentrated state visit distribution, indicating higher behavioral consistency and stability. In some complex downstream tasks, the skills with higher behavioral consistency exhibit superior performance.