In online advertising under the cost-per-conversion (CPA) model, accurate conversion rate (CVR) prediction is crucial. A major challenge is delayed feedback, where conversions may occur long after user interactions, leading to incomplete recent data and biased model training. Existing solutions partially mitigate this issue but often rely on auxiliary models, making them computationally inefficient and less adaptive to user interest shifts. We propose IF-DFM, an Influence Function-empowered for Delayed Feedback Modeling which estimates the impact of newly arrived and delayed conversions on model parameters, enabling efficient updates without full retraining. By reformulating the inverse Hessian-vector-product as an optimization problem, IF-DFM achieves a favorable trade-off between scalability and effectiveness. Experiments on benchmark datasets show that IF-DFM outperforms prior methods in both accuracy and adaptability.

Pretrained equivariant graph neural networks based on spherical harmonics offer efficient and accurate alternatives to computationally expensive ab-initio methods, yet adapting them to new tasks and chemical environments still requires fine-tuning. Conventional parameter-efficient fine-tuning (PEFT) techniques, such as Adapters and LoRA, typically break symmetry, making them incompatible with those equivariant architectures. ELoRA, recently proposed, is the first equivariant PEFT method. It achieves improved parameter efficiency and performance on many benchmarks. However, the relatively high degrees of freedom it retains within each tensor order can still perturb pretrained feature distributions and ultimately degrade performance. To address this, we present Magnitude-Modulated Equivariant Adapter (MMEA), a novel equivariant fine-tuning method which employs lightweight scalar gating to modulate feature magnitudes on a per-order and per-multiplicity basis. We demonstrate that MMEA preserves strict equivariance and, across multiple benchmarks, consistently improves energy and force predictions to state-of-the-art levels while training fewer parameters than competing approaches. These results suggest that, in many practical scenarios, modulating channel magnitudes is sufficient to adapt equivariant models to new chemical environments without breaking symmetry, pointing toward a new paradigm for equivariant PEFT design.

Sequential recommendation aims to predict the next item of interest for a user, based on her/his interaction history. In conventional sequential recommenders, a common approach is to learn sequence representations based on ID embeddings of items, which can be leveraged to predict the subsequent items of interest. Clearly, the sequence representations encode user behavioral patterns, which are critical to recommendation. Inspired by recent success in empowering Large Language Models (LLMs) to understand diverse modality (e.g., image, audio), a compelling question arises: “Can LLMs understand and utilize representations from conventional recommenders?” To answer this, we propose RecInterpreter, which examines the capacity of LLMs to decipher the representation space of pretrained recommenders. Specifically, with the multimodal pairs (i.e., interaction sequence representations and text narrations), RecInterpreter first uses a lightweight projector to map the representations into the token embedding space of the LLM, encouraging LLM to generate textual narrations for items within the sequence. Furthermore, upon interpreting recommenders, LLM can enhance its recommendation capabilities through fine-tuning with the projected representations, even without textual description of interaction sequences. Experiments showcase that RecInterpreter enhances LLMs to understand hidden representations from ID-based sequential recommenders and better accomplish recommendation task with the explicit understanding of behavior patterns.

Predicting in-hospital mortality for ICU patients is critical for improving clinical outcomes. Deep learning models have achieved remarkable accuracy but often lack explainability. To address this, we propose$X-M M P$, an eXplainable Multimodal Mortality Predictor based on transformers for heterogeneous ICU data. X-MMP integrates tabular time-series, vital signs, and clinical notes, and introduces a Layer-Wise Relevance Propagation (LRP) method to generate interpretable saliency maps across modalities. Evaluated on the multimodal MIMICIII dataset, X-MMP achieves competitive predictive performance and generates clinically meaningful explanations. Code: https://github.com/lixingqiao/XAI-ICU.

The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domains, particularly through Parameter-Efficient Fine-Tuning (PEFT) strategies like LoRA, has become a prevalent practice due to its efficiency. However, this raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information. To address these issues, we introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise parameter adjustments using influence functions. Unlike traditional unlearning techniques that are often limited in scope and require extensive retraining, LLMEraser is designed to handle a broad spectrum of unlearning tasks without compromising model performance. Extensive experiments on benchmark datasets demonstrate that LLMEraser excels in efficiently managing various unlearning scenarios while maintaining the overall integrity and efficacy of the models.

The \textbf{i}nexact \textbf{s}tochastic \textbf{p}roximal \textbf{p}oint \textbf{a}lgorithm (isPPA) is popular for solving stochastic composite optimization problems with many applications in machine learning. While the convergence theory of the (inexact) PPA has been well established, the known convergence guarantees of isPPA require restrictive assumptions. In this paper, we establish the stability and almost sure convergence of isPPA under mild assumptions, where smoothness and (restrictive) strong convexity of the objective function are not required. Imposing a local Lipschitz condition on component functions and a quadratic growth condition on the objective function, we establish last-iterate iteration complexity bounds of isPPA regarding the distance to the solution set and the Karush–Kuhn–Tucker (KKT) residual. Moreover, we show that the established iteration complexity bounds are tight up to a constant by explicitly analyzing the bounds for the regularized Fr\'echet mean problem. We further validate the established convergence guarantees of isPPA by numerical experiments.

Diffusion models have shown significant potential in generating oracle items that best match user preference with guidance from user historical interaction sequences.However, the quality of guidance is often compromised by unpredictable missing data in observed sequence, leading to suboptimal item generation.Since missing data is uncertain in both occurrence and content, recovering it is impractical and may introduce additional errors.To tackle this challenge, we propose a novel dual-side Thompson sampling-based Diffusion Model (TDM), which simulates extra missing data in the guidance signals and allows diffusion models to handle existing missing data through extrapolation.To preserve user preference evolution in sequences despite extra missing data, we introduce Dual-side Thompson Sampling to implement simulation with two probability models, sampling by exploiting user preference from both item continuity and sequence stability.TDM strategically removes items from sequences based on dual-side Thompson sampling and treats these edited sequences as guidance for diffusion models, enhancing models' robustness to missing data through consistency regularization.Additionally, to enhance the generation efficiency, TDM is implemented under the denoising diffusion implicit models to accelerate the reverse process.Extensive experiments and theoretical analysis validate the effectiveness of TDM in addressing missing data in sequential recommendations.Our data and code is available at https

In this paper, we propose a randomly projected convex clustering model for clustering a collection of $n$ high dimensional data points in $\mathbb{R}^d$ with $K$ hidden clusters. Compared to the convex clustering model for clustering original data with dimension $d$, we prove that, under some mild conditions, the perfect recovery of the cluster membership assignments of the convex clustering model, if exists, can be preserved by the randomly projected convex clustering model with embedding dimension $m = O(\epsilon^{-2}\log(n))$, where $\epsilon > 0$ is some given parameter. We further prove that the embedding dimension can be improved to be $O(\epsilon^{-2}\log(K))$, which is independent of the number of data points. We also establish the recovery guarantees of our proposed model with uniform weights for clustering a mixture of spherical Gaussians. Extensive numerical results demonstrate the robustness and superior performance of the randomly projected convex clustering model. The numerical results will also demonstrate that the randomly projected convex clustering model can outperform other popular clustering models on the dimension-reduced data, including the randomly projected K-means model.

This paper proposes an efficient HOT algorithm for solving the optimal transport (OT) problems with finite supports. We particularly focus on an efficient implementation of the HOT algorithm for the case where the supports are in $\mathbb {R}^{2}$R2 with ground distances calculated by $L_{2}^{2}$L22-norm. Specifically, we design a Halpern accelerating algorithm to solve the equivalent reduced model of the discrete OT problem. Moreover, we derive a novel procedure to solve the involved linear systems in the HOT algorithm in linear time complexity. Consequently, we can obtain an $\varepsilon$ɛ-approximate solution to the optimal transport problem with $M$M supports in $O(M^{1.5}/\varepsilon )$O(M1.5/ɛ) flops, which significantly improves the best-known computational complexity. We further propose an efficient procedure to recover an optimal transport plan for the original OT problem based on a solution to the reduced model, thereby overcoming the limitations of the reduced OT model in applications that require the transport plan. We implement the HOT algorithm in PyTorch and extensive numerical results show the superior performance of the HOT algorithm compared to existing state-of-the-art algorithms for solving the OT problems.

This article discovers that the neural network (NN) with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and -data DB variability, are proposed to measure the DB variability from the algorithm and data perspectives. Extensive experiments show significant negative correlations between the DB variability and the generalizability. From the theoretical view, two lower bounds based on algorithm DB variability are proposed and do not explicitly depend on the sample size. We also prove an upper bound of order based on data DB variability. The bound is convenient to estimate without the requirement of labels and does not explicitly depend on the network size which is usually prohibitively large in deep learning.

Keqin Peng, Liang Ding, Yancheng Yuan, Xuebo Liu, Min Zhang, Yuanxin Ouyang, Dacheng Tao. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading to very limited certifying performance. In this paper, we present the first collective certificate, which certifies a set of target nodes simultaneously. To achieve it, we formulate the problem as a binary integer quadratic constrained linear programming (BQCLP). We further develop a customized linearization technique that allows us to relax the BQCLP into linear programming (LP) that can be efficiently solved. Through comprehensive experiments, we demonstrate that our collective certification scheme significantly improves certification performance with minimal computational overhead. For instance, by solving the LP within 1 minute on the Citeseer dataset, we achieve a significant increase in the certified ratio from 0.0% to 81.2% when the injected node number is 5% of the graph size. Our paper marks a crucial step towards making provable defense more practical. Our source code is available at https://github.com/Yuni-Lai/CollectiveLPCert.

Sequential recommendation aims to predict users' next interaction with items based on their past engagement sequence. Recently, the advent of Large Language Models (LLMs) has sparked interest in leveraging them for sequential recommendation, viewing it as language modeling. Previous studies represent items within LLMs' input prompts as either ID indices or textual metadata. However, these approaches often fail to either encapsulate comprehensive world knowledge or exhibit sufficient behavioral understanding. To combine the complementary strengths of conventional recommenders in capturing behavioral patterns of users and LLMs in encoding world knowledge about items, we introduce Large Language-Recommendation Assistant (LLaRA). Specifically, it uses a novel hybrid prompting method that integrates ID-based item embeddings learned by traditional recommendation models with textual item features. Treating the "sequential behaviors of users" as a distinct modality beyond texts, we employ a projector to align the traditional recommender's ID embeddings with the LLM's input space. Moreover, rather than directly exposing the hybrid prompt to LLMs, a curriculum learning strategy is adopted to gradually ramp up training complexity. Initially, we warm up the LLM using text-only prompts, which better suit its inherent language modeling ability. Subsequently, we progressively transition to the hybrid prompts, training the model to seamlessly incorporate the behavioral knowledge from the traditional sequential recommender into the LLM. Empirical results validate the effectiveness of our proposed framework. Codes are available at https://github.com/ljy0ustc/LLaRA.

Sequential recommendation aims to recommend the next item that matches a user’s interest, based on the sequence of items he/she interacted with before. Scrutinizing previous studies, we can summarize a common learning-to-classify paradigm— given a positive item, a recommender model performs negative sampling to add negative items and learns to classify whether the user prefers them or not, based on his/her historical interaction sequence. Although effective, we reveal two inherent limitations: (1) it may differ from human behavior in that a user could imagine an oracle item in mind and select potential items matching the oracle; and (2) the classification is limited in the candidate pool with noisy or easy supervision from negative samples, which dilutes the preference signals towards the oracle item. Yet, generating the oracle item from the historical interaction sequence is mostly unexplored. To bridge the gap, we reshape sequential recommendation as a learning-to-generate paradigm, which is achieved via a guided diffusion model, termed DreamRec. Specifically, for a sequence of historical items, it applies a Transformer encoder to create guidance representations. Noising target items explores the underlying distribution of item space; then, with the guidance of historical interactions, the denoising process generates an oracle item to recover the positive item, so as to cast off negative sampling and depict the true preference of the user directly. We evaluate the effectiveness of DreamRec through extensive experiments and comparisons with existing methods. Codes and data are open-sourced at https://github.com/YangZhengyi98/DreamRec.

Collaborative Filtering (CF) models, despite their great success, suffer from severe performance drops due to popularity distribution shifts, where these changes are ubiquitous and inevitable in real-world scenarios. Unfortunately, most leading popularity debiasing strategies, rather than tackling the vulnerability of CF models to varying popularity distributions, require prior knowledge of the test distribution to identify the degree of bias and further learn the popularity-entangled representations to mitigate the bias. Consequently, these models result in significant performance benefits in the target test set, while dramatically deviating the recommendation from users’ true interests without knowing the popularity distribution in advance. In this work, we propose a novel learning framework, Invariant Collaborative Filtering (InvCF), to discover disentangled representations that faithfully reveal the latent preference and popularity semantics without making any assumption about the popularity distribution. At its core is the distillation of unbiased preference representations (i.e., user preference on item property), which are invariant to the change of popularity semantics, while filtering out the popularity feature that is unstable or outdated. Extensive experiments on five benchmark datasets and four evaluation settings (i.e., synthetic long-tail, unbiased, temporal split, and out-of-distribution evaluations) demonstrate that InvCF outperforms the state-of-the-art baselines in terms of popularity generalization ability on real recommendations. Visualization studies shed light on the advantages of InvCF for disentangled representation learning. Our codes are available at https://github.com/anzhang314/InvCF.

Knowledge graph (KG) plays an increasingly important role in recommender systems. A recent technical trend is to develop end-to-end models founded on graph neural networks (GNNs). However, existing GNN-based models are coarse-grained in relational modeling, failing to (1) identify user-item relation at a fine-grained level of intents, and (2) exploit relation dependencies to preserve the semantics of long-range connectivity.

Clustering is a fundamental problem in unsupervised learning. Popular methods like K-means, may suffer from poor performance as they are prone to get stuck in its local minima. Recently, the sum-of-norms (SON) model (also known as the convex clustering model) has been proposed by Pelckmans et al. (2005), Lindsten et al. (2011) and Hocking et al. (2011). The perfect recovery properties of the convex clustering model with uniformly weighted all-pairwise-differences regularization have been proved by Zhu et al. (2014) and Panahi et al. (2017). However, no theoretical guarantee has been established for the general weighted convex clustering model, where better empirical results have been observed. In the numerical optimization aspect, although algorithms like the alternating direction method of multipliers (ADMM) and the alternating minimization algorithm (AMA) have been proposed to solve the convex clustering model (Chi and Lange, 2015), it still remains very challenging to solve large-scale problems. In this paper, we establish sufficient conditions for the perfect recovery guarantee of the general weighted convex clustering model, which include and improve existing theoretical results in (Zhu et al., 2014; Panahi et al., 2017) as special cases. In addition, we develop a semismooth Newton based augmented Lagrangian method for solving large-scale convex clustering problems. Extensive numerical experiments on both simulated and real data demonstrate that our algorithm is highly efficient and robust for solving large-scale problems. Moreover, the numerical results also show the superior performance and scalability of our algorithm comparing to the existing first-order methods. In particular, our algorithm is able to solve a convex clustering problem with 200,000 points in $\mathbb{R}^3$ in about 6 minutes.

Clustering is a fundamental problem in unsupervised learning. Popular methods like K-means, may suffer from instability as they are prone to get stuck in its local minima. Recently, the sumof-norms (SON) model (also known as clustering path), which is a convex relaxation of hierarchical clustering model, has been proposed in (Lindsten et al., 2011) and (Hocking et al., 2011). Although numerical algorithms like alternating direction method of multipliers (ADMM) and alternating minimization algorithm (AMA) have been proposed to solve convex clustering model (Chi & Lange, 2015), it is known to be very challenging to solve large-scale problems. In this paper, we propose a semismooth Newton based augmented Lagrangian method for large-scale convex clustering problems. Extensive numerical experiments on both simulated and real data demonstrate that our algorithm is highly efficient and robust for solving large-scale problems. Moreover, the numerical results also show the superior performance and scalability of our algorithm comparing to existing first-order methods.

Image segmentation with user inputs gets more and more popular in recent years and always performs better compared with automatic methods. However, existing interactive image segmentation methods still might fail if the image contains messy textures, or the user inputs are sparse or at inappropriate locations. In this paper, we propose a novel iterative refinement framework which leads to robust segmentation performance even with sparse and improper input strokes. Specifically, a geodesic distance based energy is introduced and combined with convex active contour model, and an iterative seeds refinement technique is put forward to handle the sparse input problem. Extensive experiments using real world images, and segmentation benchmark dataset show that our proposed method has superior performance compared with representative state-of-the-art methods.