Recommender systems require on-demand unlearning of user-item interactions to meet privacy regulations without sacrificing recommendation quality. Existing approaches either retrain large models at prohibitive cost or apply local parameter tweaks that misestimate non-linear effects, resulting in degraded accuracy, poor scalability for bulk deletions, and no formal privacy auditing. We present ReCUR, a Recommendation Contrastive Unlearning framework with Influence Estimation that addresses these weaknesses. ReCUR first applies a contrastive push-pull loss to push forgotten interaction embeddings away and pull retained ones back toward their original anchors. This not only subtracts deleted interactions’ contributions from the model, but yields fine-grained forgetting control, minimizes collateral drift, and recovers lost utility without full retraining. To compensates for any lost utility and promote fairness, ReCUR introduces a re-ranking mechanism with group-specific promotion weights that rebalance recommendations for diverse and niche user segments. Across four real-world datasets, ReCUR matches or exceeds retrain-from-scratch accuracy, retaining over 95% utility even after deleting up to 20% of interactions, while achieving up to an order-of-magnitude speed-up. Membership-inference audits confirm ReCUR’s unlearned models are indistinguishable from fresh retrains, offering strong empirical privacy guarantees. Our further analysis reveals intuitive trade-offs between forgetting strength and utility, and shows that promoting under-represented users enhances overall accuracy.

Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresponding rays. To capture the inherent uncertainties in sparse-view pose inference, we adapt this approach to learn a denoising diffusion model which allows us to sample plausible modes while improving performance. Our proposed methods, both regression- and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D while generalizing to unseen object categories and in-the-wild captures.

In today’s data-rich era, large models continuously consume vast troves of personal data, raising pertinent questions about user consent and its implications in training machine learning frameworks. With mounting calls for enhanced user privacy, the “right to be forgotten” is gaining traction in contemporary research. Parallelly, the ubiquity of graph neural networks underscores its ever-growing imprint on artificial intelligence communities, resonating in almost every facet of various applications. This study delves into enhancing the effectiveness of graph unlearning through the incorporation of graph contrastive learning. To adeptly erase edge information without compromising the performance of the subsequent link prediction task. We present a novel graph unlearning framework, Graph Contrastive Unlearning (GCU). Infusing the principles of contrastive learning into conventional graph unlearning paradigms, the GCU stands out, ensuring the absolute erasure of deleted edge data. The genius of graph contrastive unlearning lies in its dual capability: facilitating the model in discerning the deleted edges from their original counterparts while seamlessly aligning the neighbors of these edges with the original graph’s node features. Crafted meticulously, the GCU extirpates the influence of the removed elements from model parameters and neighboring representations. Yet, it ensures the sanctity and retention of the residual model knowledge post-deletion. Empirical tests underscore the GCU’s promising edge unlearning ability, revealing marked improvements in link prediction across diverse graph datasets. This not only fortifies user privacy but also streamlines the unlearning process, eliminating the cumbersome need for full model retraining even in scenarios of mass edge deletions.

A buck converter with good load regulation and spur-free on-time generator (SFOTG) is presented in this work. The proposed control scheme adopts an additional current feed-forward circuit and a type-II compensator to eliminate dependency on the equivalent series resistance (RESR) of the output capacitor (COUT) to ensure an accurate output voltage (VOUT). Furthermore, SFOTG is employed to reduce electromagnetic interference (EMI) effects for noise-sensitive applications. This work is implemented in the TSMC 0.18-μm CMOS process. The chip active area is 0.7 mm2. Experimental results demonstrate the load regulation of 1.8 mV/A, and 20.73-dB improvement of the output spurs compared to that of a conventional COT buck converter. The peak efficiency is 89.1% at 300 mA load current.