Objective. Deformable image registration (DIR) is critical in many medical imaging applications. Diffeomorphic transformations, which are smooth invertible mappings with smooth inverses preserve topological properties and are an anatomically plausible means of constraining the solution space in many settings. Traditional iterative optimization-based diffeomorphic DIR algorithms are computationally costly and are not able to consistently resolve large and complicated deformations in medical image registration. Convolutional neural network implementations can rapidly estimate the transformation in through a pre-trained model. However, the structure design of most neural networks for DIR fails to systematically enforce diffeomorphism and inverse consistency. In this paper, a novel unsupervised neural network structure is proposed to perform a fast, accurate, and inverse-consistent diffeomorphic DIR. Approach. This paper introduces a novel unsupervised inverse-consistent diffeomorphic registration network termed IConDiffNet, which incorporates an energy constraint that minimizes the total energy expended during the deformation process. The IConDiffNet architecture consists of two symmetric paths, each employing multiple recursive cascaded updating blocks (neural networks) to handle different virtual time steps parameterizing the path from the initial undeformed image to the final deformation. These blocks estimate velocities corresponding to specific time steps, generating a series of smooth time-dependent velocity vector fields. Simultaneously, the inverse transformations are estimated by corresponding blocks in the inverse path. By integrating these series of time-dependent velocity fields from both paths, optimal forward and inverse transformations are obtained, aligning the image pair in both directions. Main result. Our proposed method was evaluated on a three-dimensional inter-patient image registration task with a large-scale brain MRI image dataset containing 375 subjects. The proposed IConDiffNet achieves fast and accurate DIR with better DSC, lower Hausdorff distance metric, and lower total energy spent during the deformation in the test dataset compared to competing state-of-the-art deep-learning diffeomorphic DIR approaches. Visualization shows that IConDiffNet produces more complicated transformations that better align structures than the VoxelMorph-Diff, SYMNet, and ANTs-SyN methods. Significance. The proposed IConDiffNet represents an advancement in unsupervised deep-learning-based DIR approaches. By ensuring inverse consistency and diffeomorphic properties in the outcome transformations, IConDiffNet offers a pathway for improved registration accuracy, particularly in clinical settings where diffeomorphic properties are crucial. Furthermore, the generality of IConDiffNet’s network structure supports direct extension to diverse 3D image registration challenges. This adaptability is facilitated by the flexibility of the objective function used in optimizing the network, which can be tailored to suit different registration tasks.
The post-click Conversion Rate (CVR) prediction plays a pivotal role in industrial recommender systems, directly serving as a decisive factor for ranking strategies and revenue optimization. While Entire Space Multi-Task Models (e.g., ESMM) have become the dominant framework by effectively addressing sample selection bias and data sparsity, they rely heavily on the assumption that the observed click and conversion labels perfectly reflect user preferences. In real-world scenarios, however, observed data is inevitably contaminated by label noise. Crucially, within the entire space modeling framework, this noise exhibits a complex hierarchical structure, where the superimposition of noise from antecedent click labels and subsequent conversion labels results in conventional single-task denoising methods being ineffective. To bridge this gap, we propose HiDe-ESMM (Hierarchical Denoising Entire Space Multi-Task Model), a unified framework designed to systematically mitigate hierarchical label noise. First, adopting the loss correction paradigm, we derive a statistically unbiased CTCVR loss via backward correction and identify the requisite noise rates based on the weak separability assumption. Second, to alleviate the numerical instability inherent in the unbiased loss approach, we introduce a robust forward correction strategy as an efficient alternative and theoretically prove the consistency of its optimal solution with the optimal solution on clean data. Extensive experiments on one semi-synthetic dataset and two real-world industrial datasets demonstrate that HiDe-ESMM significantly outperforms state-of-the-art baselines, validating its robustness in handling hierarchical noisy labels.
Due to limited user attention and platform presentation capacity, each user can attend to only a limited number of displayed items, making the per-user recommendation slot a scarce resource. Allocating a scarce recommendation slot to a certain item that a user would have purchased regardless of the intervention leads to a waste-of-slots problem. Conventional uplift modeling approaches primarily optimize uplift-driven metrics under global constraints and are developed based on structured data settings. However, such frameworks provide insufficient differentiation under strictly localized limitations among the vast number of candidate interactions, failing to characterize their underlying economic consequences arising from distinct user-item interaction response patterns, which yield divergent compositions of net increments from valid interventions and potential resource waste induced by invalid interventions. To address these challenges, we formulate per-user slot-constrained recommendation allocation from a counterfactual perspective. We propose identification methods for the probabilities of interaction-level counterfactual response strata and reveal their heterogeneous intervention-induced consequences. We develop a counterfactual stratum-aware treatment allocation learning approach with economic interpretation of the proposed stratum-weighted objective, establish theoretical optimality guarantees, and derive a finite-sample reward lower bound of the learned policy. We implement this allocation principle in CORA-CLM, standing for Causal LLM for Counterfactual Optimal Recommendation Allocation under Per-user Constraints, an intelligent text-based allocation system for recommendation scenarios, integrating LLM-based semantic parsing and an adaptive entropy-based coarse filtering strategy to substantially reduce LLM API calls and ensure computational viability for practical deployment. Extensive experiments on both synthetic and semi-synthetic datasets based on real-world data demonstrate the effectiveness of our framework under per-user recommendation slot constraints.
The lack of explicit negative labels issue is a prevalent challenge in numerous domains, including CV, NLP, and Recommender Systems (RSs). To address this challenge, many negative sample completion methods are proposed, such as optimizing sample distribution through pseudo-negative sampling and confidence screening in CV, constructing reliable negative examples by leveraging textual semantics in NLP, and supplementing negative samples via sparsity analysis of user interaction behaviors and preference inference in RS for handling implicit feedback. However, most existing methods fail to adequately address the Missing-Not-At-Random (MNAR) nature of the data and the potential presence of unmeasured confounders, which compromise model robustness in practice. In this paper, we first formulate the prediction task in RS with implicit feedback as a positive-unlabeled (PU) learning problem. We then propose a two-phase debiasing framework consisting of exposure status imputation, followed by debiasing through the proposed doubly robust estimator. Moreover, our theoretical analysis shows that existing propensity-based approaches are biased in the presence of unmeasured confounders. To overcome this, we incorporate a robust deconfounding method in the debiasing phase to effectively mitigate the impact of unmeasured confounders. We conduct extensive experiments on three widely used real-world datasets to demonstrate the effectiveness and potential of the proposed methods.