Prior research on neural architecture search (NAS) for adversarial robustness has revealed that a lightweight and adversarially robust sub-network could exist in a non-robust large teacher network. Such a sub-network is generally discovered based on heuristic rules to perform neural architecture search. However, heuristic rules are inadequate to handle diverse adversarial attacks and different "teacher" network capacity. To address this key challenge, we propose Reinforced Compressive Neural Architecture Search (RC-NAS), aiming to achieve Versatile Adversarial Robustness. Specifically, we define novel task settings that compose datasets, adversarial attacks, and teacher network configuration. Given diverse tasks, we develop an innovative dual-level training paradigm that consists of a meta-training and a fine-tuning phase to effectively expose the RL agent to diverse attack scenarios (in meta-training), and make it adapt quickly to locate an optimal sub-network (in fine-tuning) for previously unseen scenarios. Experiments show that our framework could achieve adaptive compression towards different initial teacher networks, datasets, and adversarial attacks, resulting in more lightweight and adversarially robust architectures. We also provide a theoretical analysis to explain why the reinforcement learning (RL)-guided adversarial architectural search helps adversarial robustness over standard adversarial training methods.

Vision-language models, pre-trained on web-scale datasets, have the potential to greatly enhance the intelligence of web applications (e.g., search engines, chatbots, and art tools). Precisely, these models align disparate domains into a co-embedding space, achieving impressive zero-shot performance on multi-modal tasks (e.g., image-text retrieval, VQA). However, existing methods often rely on well-prepared data that less frequently contain noise and variability encountered in real-world scenarios, leading to severe performance drops in handling out-of-distribution (OOD) samples. This work first comprehensively analyzes the performance drop between in-distribution (ID) and OOD retrieval. Based on empirical observations, we introduce a novel approach, Evidential Language-Image Posterior (ELIP), to achieve robust alignment between web images and semantic knowledge across various OOD cases by leveraging evidential uncertainties. The proposed ELIP can be seamlessly integrated into general image-text contrastive learning frameworks, providing an efficient fine-tuning approach without exacerbating the need for additional data. To validate the effectiveness of ELIP, we systematically design a series of OOD cases (e.g., image distortion, spelling errors, and a combination of both) on two benchmark datasets to mimic noisy data in real-world web applications. Our experimental results demonstrate that ELIP improves the performance and robustness of mainstream pre-trained vision-language models facing OOD samples in image-text retrieval tasks.

In recent information retrieval systems, it is observed that the datasets used to train machine learning models can be biased, leading to systematic discrimination against certain demographic groups, which means the ranking utility of specific groups is often lower than others in a biased dataset. Training models on these datasets will further decrease the exposure of the minority groups. To address this problem, we propose a Meta Curriculum-based Fair Ranking framework (MCFR) which could alleviate the data bias issue through the weighted loss using gradient-based learning to learn. Specifically, we optimize a meta learner from a sampled dataset (meta-dataset), and meanwhile train a ranking model on the whole (biased) dataset. The meta-dataset is sampled with a curriculum learning scheduler to guide the meta learner's training to gradually mitigate the skewness towards biased attributes. The meta learner serves as a weighting function to make the ranking loss focus more on the minority group. We formulate the proposed MCFR as a bilevel optimization problem and solve it using gradients through gradients. Extensive experiments on real-world datasets demonstrate that our approach can be used as a generic framework to work with various ranking losses and fairness metrics.

Data selection bias has been a long-lasting challenge in the machine learning domain, especially in multi-stage recommendation systems, where the distribution of labeled items for model training is very different from that of the actual candidates during inference time. This distribution shift is even more prominent in the context of online advertising where the user base is diverse and the platform contains a wide range of contents. In this paper, we first investigate the data selection bias in the upper funnel (Ads Retrieval) of Pinterest's multi-cascade ads ranking system. We then conduct comprehensive experiments to assess the performance of various state-of-the-art methods, including transfer learning, adversarial learning, and unsupervised domain adaptation. Moreover, we further introduce some modifications into the unsupervised domain adaptation and evaluate the performance of different variants of this modified method. Our online A/B experiments show that the modified version of unsupervised domain adaptation (MUDA) could provide the largest improvements to the performance of Pinterest's advertisement ranking system compared with other methods and the one used in current production.

Fairness has gained increasing importance in a variety of AI and machine learning contexts. As one of the most ubiquitous applications of machine learning, search engines mediate much of the information experiences of members of society. Consequently, understanding and mitigating potential algorithmic unfairness in search have become crucial for both users and systems. In this tutorial, we will introduce the fundamentals of fairness in machine learning, for both supervised learning such as classification and ranking, and unsupervised learning such as clustering. We will then present the existing work on fairness in search engines, including the fairness definitions, evaluation metrics, and taxonomies of methodologies. This tutorial will help orient information retrieval researchers to algorithmic fairness, provide an introduction to the growing literature on this topic, and gathering researchers and practitioners interested in this research direction.

Automated graph learning has drawn widespread research attention due to its great potential to reduce human efforts when dealing with graph data, among which hyperparameter optimization (HPO) is one of the mainstream directions and has made promising progress. However, how to obtain reliable and trustworthy prediction results with automated graph neural networks (GNN) is still quite underexplored. To this end, we investigate automated GNN calibration by marrying uncertainty estimation to the HPO problem. Specifically, we propose a hyperparameter uncertainty-induced graph convolutional network (HyperU-GCN) with a bilevel formulation, where the upper-level problem explicitly reasons uncertainties by developing a probabilistic hypernetworks through a variational Bayesian lens, while the lower-level problem learns how the GCN weights respond to a hyperparameter distribution. By squeezing model uncertainty into the hyperparameter space, the proposed HyperU-GCN could achieve calibrated predictions in a similar way to Bayesian model averaging over hyperparameters. Extensive experimental results on six public datasets were provided in terms of node classification accuracy and expected calibration error (ECE), demonstrating the effectiveness of our approach compared with several state-of-the-art uncertainty-aware and calibrated GCN methods.

Multi-modal time series classification (MTC) uses complementary information from different modalities to improve the learning performance. Obtaining informative modality-specific representation plays an essential role in MTC. Attention mechanism has been widely adopted as an effective strategy for discovering discriminative cues underlying temporal data. However, most existing MTC methods only utilize attention to balance the feature weights within or cross modalities but ignore digging latent patterns from mutual-support information in attention space. Specifically, the attention distributions are different for multiple modalities which are supportive and instructional with each other. To this end, we propose a collaborative attention mechanism (CAM) for MTC based on a novel perspective to utilize attention module. CAM detects the attention differences among multi-modal time series, and adaptively integrates different attention information to benefit each other. We extend the long short-term memory (LSTM) to a Mutual-Aid RNN (MAR) for multi-modal collaboration. CAM takes advantages of modality-specific attention to guide another modality and discover potential information which is hard to be explored by itself. It paves a novel way of employing attention to enhance the capacity of multi-modal representations. Extensive experiments on four multi-modal time series datasets illustrate the CAM effectiveness to improve the single-modal and also boost multi-modal performances.

In recent years, the fairness in information retrieval (IR) system has received increasing research attention. While the data-driven ranking models achieve significant improvements over traditional methods, the dataset used to train such models is usually biased, which causes unfairness in the ranking models. For example, the collected imbalance dataset on the subject of the expert search usually leads to systematic discrimination on the specific demographic groups such as race, gender, etc, which further reduces the exposure for the minority group. To solve this problem, we propose a Meta-learning based Fair Ranking (MFR) model that could alleviate the data bias for protected groups through an automatically-weighted loss. Specifically, we adopt a meta-learning framework to explicitly train a meta-learner from an unbiased sampled dataset (meta-dataset), and simultaneously, train a listwise learning-to-rank (LTR) model on the whole (biased) dataset governed by "fair" loss weights. The meta-learner serves as a weighting function to make the ranking loss attend more on the minority group. To update the parameters of the weighting function and the ranking model, we formulate the proposed MFR as a bilevel optimization problem and solve it using the gradients through gradients. Experimental results on several real-world datasets demonstrate that the proposed method achieves a comparable ranking performance and significantly improves the fairness metric compared with state-of-the-art methods.

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several representative baselines.

Modeling user behavior from unstructured software log-trace data is critical in providing personalized service (\emphe.g., cross-platform recommendation). Existing user modeling approaches cannot well handle the long-term temporal information in log data, or produce semantically meaningful results for interpreting user logs. To address these challenges, we propose a Log2Intent framework for interpretable user modeling in this paper. Log2Intent adopts a deep sequential modeling framework that contains a temporal encoder, a semantic encoder and a log action decoder, and it fully captures the long-term temporal information in user sessions. Moreover, to bridge the semantic gap between log-trace data and human language, a recurrent semantics memory unit (RSMU) is proposed to encode the annotation sentences from an auxiliary software tutorial dataset, and the output of RSMU is fed into the semantic encoder of Log2Intent. Comprehensive experiments on a real-world Photoshop log-trace dataset with an auxiliary Photoshop tutorial dataset demonstrate the effectiveness of the proposed Log2Intent framework over the state-of-the-art log-trace user modeling method in three different tasks, including log annotation retrieval, user interest detection and user next action prediction.

Ensemble Clustering (EC) is an important topic for data cluster analysis. It targets to integrate multiple Basic Partitions (BPs) of a particular dataset into a consensus partition. Among previous works, one promising and effective way is to transform EC as a graph partitioning problem on the co-association matrix, which is a pair-wise similarity matrix summarized by all the BPs in essence. However, most existing EC methods directly utilize the co-association matrix, yet without considering various noises (e.g., the disagreement between different BPs and the outliers) that may exist in it. These noises can impair the cluster structure of a co-association matrix, and thus mislead the final graph partitioning process. To address this challenge, we propose a novel Robust Spectral Ensemble Clustering (RSEC) algorithm in this article. Specifically, we learn low-rank representation (LRR) for the co-association matrix to uncover its cluster structure and handle the noises, and meanwhile, we perform spectral clustering with the learned representation to seek for a consensus partition. These two steps are jointly proceeded within a unified optimization framework. In particular, during the optimizing process, we leverage consensus partition to iteratively enhance the block-diagonal structure of LRR, in order to assist the graph partitioning. To solve RSEC, we first formulate it by using nuclear norm as a convex proxy to the rank function. Then, motivated by the recent advances in non-convex rank minimization, we further develop a non-convex model for RSEC and provide it a solution by the majorization--minimization Augmented Lagrange Multiplier algorithm. Experiments on 18 real-world datasets demonstrate the effectiveness of our algorithm compared with state-of-the-art methods. Moreover, several impact factors on the clustering performance of our approach are also explored extensively.

Multi-view clustering, as one of the most important methods to analyze multi-view data, has been widely used in many real-world applications. Most existing multi-view clustering methods perform well on the assumption that each sample appears in all views. Nevertheless, in real-world application, each view may well face the problem of the missing data due to noise, or malfunction. In this paper, a new consistent generative adversarial network is proposed for partial multi-view clustering. We learn a common low-dimensional representation, which can both generate the missing view data and capture a better common structure from partial multi-view data for clustering. Different from the most existing methods, we use the common representation encoded by one view to generate the missing data of the corresponding view by generative adversarial networks, then we use the encoder and clustering networks. This is intuitive and meaningful because encoding common representation and generating the missing data in our model will promote mutually. Experimental results on three different multi-view databases illustrate the superiority of the proposed method.

Graphs play an essential role in many data mining paradigms, such as semi-supervised classification. Conventional graph learning methods mainly focus on constructing graphs from single-view data. Nowadays data can be collected from multiple views using various sensors. How to construct a robust and reliable graph from multi-view data is still an open problem. In this paper, we propose a multi-view graph learning (MVGL) approach with adaptive label propagation for semi-supervised classification. MVGL integrates latent factor extraction, graph sparsification, and label propagation into a unified framework. It seeks shared latent factors from multi-view data as view-independent data representations, and then constructs a sparse graph accordingly. Meanwhile, the label propagation is adaptively optimized during graph construction. An efficient optimization algorithm is designed to solve the model. Experimental results on two benchmark datasets show remarkable improvements over both single-view and multi-view learning baselines.

Ensemble Clustering (EC) aims to integrate multiple Basic Partitions (BPs) of the same dataset into a consensus one. It could be transformed as a graph partition problem on the co-association matrix derived from BPs. However, existing EC methods usually directly use the co-association matrix, yet without considering various noises (e.g., the disagreement between different BPs or outliers) that may exist in it. These noises can impair the cluster structure of a co-association matrix and thus degrade the final clustering performance. In this paper, we propose a novel Robust Spectral Ensemble Clustering (RSEC) approach to address this challenge. First, RSEC learns a robust representation for the co-association matrix through low-rank constraint, which reveals the cluster structure of a co-association matrix and captures various noises in it. Second, RSEC finds the consensus partition by conducting spectral clustering. These two steps are iteratively performed in a unified optimization framework. Most importantly, during our optimization process, we utilize consensus partition to iteratively enhance the block-diagonal structure of the learned representation to further assist the clustering process. Experiments on numerous real-world datasets demonstrate the effectiveness of our method compared with the state-of-the-art. Moreover, several impact factors that may affect the clustering performance of our approach are also explored extensively.