In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called EncryIP, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, EncryIP demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.

Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e.g., understanding where the model comes from, how it is trained, and how it is used). Our focus is on a novel problem within this domain, namely Model Provenance (MP). MP concerns the relationship between a target model and its pre-training model and aims to determine whether a source model serves as the provenance for a target model. In this paper, we formulate this new challenge as a learning problem, supplementing our exploration with empirical discussions on its connections to existing works. Following that, we introduce “Model DNA”, an interesting concept encoding the model’s training data and input-output information to create a compact machine-learning model representation. Capitalizing on this model DNA, we establish an efficient framework consisting of three key components: DNA generation, DNA similarity loss, and a provenance classifier, aimed at identifying model provenance. We conduct evaluations on both computer vision and natural language processing tasks using various models, datasets, and scenarios to demonstrate the effectiveness of our approach.

With the rising awareness of data assets, data governance, which is to understand where data comes from, how it is collected, and how it is used, has been assuming evergrowing importance. One critical component of data governance gaining increasing attention is auditing machine learning models to determine if specific data has been used for training. Existing auditing techniques, like shadow auditing methods, have shown feasibility under specific conditions such as having access to label information and knowledge of training protocols. However, these conditions are often not met in most real-world applications. In this paper, we introduce a practical framework for auditing data provenance based on a differential mechanism, i.e., after carefully designed transformation, perturbed input data from the target model's training set would result in much more drastic changes in the output than those from the model's non-training set. Our framework is data-dependent and does not require distinguishing training data from non-training data or training additional shadow models with labeled output data. Furthermore, our framework extends beyond point-based data auditing to group-based data auditing, aligning with the needs of realworld applications. Our theoretical analysis of the differential mechanism and the experimental results on real-world data sets verify the proposal's effectiveness. The codes have been uploaded in an anonymous link.

Machine learning models have liberated manpower greatly in many real-world tasks, but their predictions are still worse than humans on some specific instances. To improve the performance, it is natural to optimize machine learning models to take decisions for most instances while delivering a few tricky instances to humans, resulting in the problem of Human Assisted Learning (HAL). Previous works mainly formulated HAL as a constrained optimization problem that tries to find a limited subset of instances for human decision such that the sum of model and human errors can be minimized; and employed the greedy algorithms, whose performance, however, may be limited due to the greedy nature. In this paper, we propose a new framework HAL-EMO based on Evolutionary Multi-objective Optimization, which reformulates HAL as a bi-objective optimization problem that minimizes the number of selected instances for human decision and the total errors simultaneously, and employs a Multi-Objective Evolutionary Algorithm (MOEA) to solve it. We implement HAL-EMO using two MOEAs, the popular NSGA-II as well as the theoretically grounded GSEMO. We also propose a specific MOEA, called BSEMO, with biased selection and balanced mutation for HAL-EMO, and prove that for human assisted regression and classification, HAL-EMO using BSEMO can achieve better and same theoretical guarantees than previous greedy algorithms, respectively. Experiments on the tasks of medical diagnosis and content moderation show the superiority of HAL-EMO (with either NSGA-II, GSEMO or BSEMO) over previous algorithms, and that using BSEMO leads to the best performance of HAL-EMO.

Script event prediction aims to predict the subsequent event given the context. This requires the capability to infer the correlations between events. Recent works have attempted to improve event correlation reasoning by using pretrained language models and incorporating external knowledge (e.g., discourse relations). Though promising results have been achieved, some challenges still remain. First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well. Second, modeling correlations between events with discourse relations is limited because it can only capture explicit correlations between events with discourse markers, and cannot capture many implicit correlations. To this end, we propose a novel generative approach for this task, in which a pretrained language model is fine-tuned with an event-centric pretraining objective and predicts the next event within a generative paradigm. Specifically, we first introduce a novel event-level blank infilling strategy as the learning objective to inject event-level knowledge into the pretrained language model, and then design a likelihood-based contrastive loss for fine-tuning the generative model. Instead of using an additional prediction layer, we perform prediction by using sequence likelihoods generated by the generative model. Our approach models correlations between events in a soft way without any external knowledge. The likelihood-based prediction eliminates the need to use additional networks to make predictions and is somewhat interpretable since it scores each word in the event. Experimental results on the multi-choice narrative cloze (MCNC) task demonstrate that our approach achieves better results than other state-of-the-art baselines. Our code will be available at https://github.com/zhufq00/mcnc.

Multilingual biomedical entity linking (MBEL) aims to map language-specific mentions in the biomedical text to standardized concepts in a multilingual knowledge base (KB) such as Unified Medical Language System (UMLS).In this paper, we propose Con2GEN, a prompt-based controllable contrastive generation framework for MBEL, which summarizes multidimensional information of the UMLS concept mentioned in biomedical text into a natural sentence following a predefined template.Instead of tackling the MBEL problem with a discriminative classifier, we formulate it as a sequence-tosequence generation task, which better exploits the shared dependencies between source mentions and target entities.Moreover, Con2GEN matches against UMLS concepts in as many languages and types as possible, hence facilitating cross-information disambiguation.Extensive experiments show that our model achieves promising performance improvements compared with several state-of-the-art techniques on the XL-BEL and the Mantra GSC datasets spanning 12 typologically diverse languages.

Data is one of the most critical resources in the AI Era. While substantial research has been dedicated to training machine learning models using various types of data, much less efforts have been invested in the exploration of assessing and governing data assets in end-to-end processes of machine learning and data science, that is, the pipeline where data is collected and processed, and then machine learning models are produced, requested, deployed, shared and evolved. To provide a state-of-the-art overall picture of this important and novel area and advocate the related research and development, we present a tutorial addressing two essential problems. First, in the pipeline of machine learning, how can data and machine learning models be priced properly so that contributions from various parties can be assessed and recognized in a fair manner? Second, in the collaboration among many parties in building, distributing and sharing machine learning models, how can data as assets be managed? Accordingly, the first part of our proposal surveys data and model pricing in the pipeline of machine learning, while the second part discusses data asset governance for collaborative artificial intelligence. Each part is self-contained. At the same time, the two parts echo each other and connect a series of interesting and important problems into a dynamic big picture.

Diverse applications involving complicated data objects such as proteins and images are solved by applying multi-instance learning (MIL) algorithms. However, few MIL algorithms can deal with problems in an open and dynamic environment, where new categories of samples emerge. In this type of emerging novel class setting, algorithms should be able to not only classify the samples from the observed classes accurately, but also recognize the samples from the novel class. In this paper, we focus on the Multi-Instance learning with Emerging Novel class (MIEN) problem, and formulate MIEN from a metric learning perspective. We extract key instances to form the “super-bag” for each observed class, and non-key instances from all the observed classes to form a “meta super-bag”. Based on these super-bags, we propose the MIEN-metric method to learn discriminative metrics for classifying MIL bags from the observed classes and recognizing bags from the novel class. Experimental results of diverse domains, e.g., biological function annotation, text categorization, and object-centric/scene-centric image classification, show MIEN-metric outperforms other baseline methods significantly when the novel class emerges. Meanwhile, MIEN-metric is comparable with state-of-the-art MIL algorithms for binary classification in the traditional MIL setting.

This paper re-examines existing systems in streaming classification with emerging new classes (SENC) problems, where new classes that have not been used to train a classifier may emerge in a data stream. We identify that existing systems have an unspecified assumption that emerging new classes are geometrically far from known classes, or instances of known classes are densely distributed, in the feature space. Using a class separation indicator alpha, we refine the SENC problem into an alpha-SENC problem, where alpha indicates a geometric distance between two classes in the feature space. We show that while most existing systems work well in high-alpha SENC problems (i.e., a new class is geometrically far from a known class or instances of known classes are densely distributed), they perform poorly in low-alpha SENC problems. To solve low-alpha SENC problems effectively, we propose an approach using nearest neighbor ensembles or SENNE. We demonstrate that SENNE is able to handle both the low-alpha and high-alpha SENC problems which can appear at different times in a single data stream.

User identity linkage (UIL), the problem of matching user account across multiple online social networks (OSNs), is widely studied and important to many real-world applications. Most existing UIL solutions adopt a supervised or semi-supervised approach which generally suffer from scarcity of labeled data. In this paper, we propose Factoid Embedding, a novel framework that adopts an unsupervised approach. It is designed to cope with different profile attributes, content types and network links of different OSNs. The key idea is that each piece of information about a user identity describes the real identity owner, and thus distinguishes the owner from other users. We represent such a piece of information by a factoid and model it as a triplet consisting of user identity, predicate, and an object or another user identity. By embedding these factoids, we learn the user identity latent representations and link two user identities from different OSNs if they are close to each other in the user embedding space. Our Factoid Embedding algorithm is designed such that as we learn the embedding space, each embedded factoid is "translated" into a motion in the user embedding space to bring similar user identities closer, and different user identities further apart. Extensive experiments are conducted to evaluate Factoid Embedding on two real-world OSNs data sets. The experiment results show that Factoid Embedding outperforms the state-of-the-art methods even without training data.

Streaming classification with emerging new class is an important problem of great research challenge and practical value. In many real applications, the task often needs to handle large matrices issues such as textual data in the bag-of-words model and large-scale image analysis. However, the methodologies and approaches adopted by the existing solutions, most of which involve massive distance calculation, have so far fallen short of successfully addressing a real-time requested task. In this paper, the proposed method dynamically maintains two low-dimensional matrix sketches to 1) detect emerging new classes; 2) classify known classes; and 3) update the model in the data stream. The update efficiency is superior to the existing methods. The empirical evaluation shows the proposed method not only receives the comparable performance but also strengthens modelling on large-scale data sets.

Point-of-Interest (POI) recommendation is an important application in Location-based Social Networks (LBSN). The category prediction problem is to predict the next POI category that users may visit. The predicted category information is critical in large-scale POI recommendation because it can significantly reduce the prediction space and improve the recommendation accuracy. While efforts have been made to address the POI category prediction problem, several important challenges still exist. First, existing solutions did not fully explore the temporal dependency (e.g., “long range dependency”) of users' check-in traces. Second, the hidden contextual information associated with each check-in point has been underutilized. In this work, we propose a Context-Aware POI Category Prediction (CAP-CP) scheme using Natural Language Processing (NLP) models. In particular, to address temporal dependency challenge, we develop a novel Temporal Adaptive Ngram (TA-Ngram) model to capture the dynamic dependency between check-in points. To address the challenge of hidden context incorporation, CAP-CP leverages the Probabilistic Latent Semantic Analysis (PLSA) model to infer the semantic implications of the context variables in the prediction model. Empirical results on a real world dataset show that our scheme can effectively improve the performance of the state-of-the-art POI recommendation solutions.

With the rapid growth of online social media and ubiquitous Internet connectivity, social sensing has emerged as a new crowdsourcing application paradigm of collecting observations (often called claims) about the physical environment from humans or devices on their behalf. A fundamental problem in social sensing applications lies in effectively ascertaining the correctness of claims and the reliability of data sources without knowing either of them a priori, which is referred to as truth discovery. While significant progress has been made to solve the truth discovery problem, some important challenges have not been well addressed yet. First, existing truth discovery solutions did not fully solve the dynamic truth discovery problem where the ground truth of claims changes over time. Second, many current solutions are not scalable to large-scale social sensing events because of the centralized nature of their truth discovery algorithms. Third, the heterogeneity and unpredictability of the social sensing data traffic pose additional challenges to the resource allocation and system responsiveness. In this paper, we developed a Scalable Streaming Truth Discovery (SSTD) solution to address the above challenges. In this paper, we developed a Scalable Streaming Truth Discovery (SSTD) solution to address the above challenges. In particular, we first developed a dynamic truth discovery scheme based on Hidden Markov Models (HMM) to effectively infer the evolving truth of reported claims. We further developed a distributed framework to implement the dynamic truth discovery scheme using Work Queue in HTCondor system. We also integrated the SSTD scheme with an optimal workload allocation mechanism to dynamically allocate the resources (e.g., cores, memories) to the truth discovery tasks based on their computation requirements. We evaluated SSTD through real world social sensing applications using Twitter data feeds. The evaluation results on three real-world data traces (i.e., Boston Bombing, Paris Shooting and College Football) show that the SSTD scheme is scalable and outperforms the state-of-the-art truth discovery methods in terms of both effectiveness and efficiency.

In traditional active learning, there is only one labeler that always returns the ground truth of queried labels. However, in many applications, multiple labelers are available to offer diverse qualities of labeling with different costs. In this paper, we perform active selection on both instances and labelers, aiming to improve the classification model most with the lowest cost. While the cost of a labeler is proportional to its overall labeling quality, we also observe that different labelers usually have diverse expertise, and thus it is likely that labelers with a low overall quality can provide accurate labels on some specific instances. Based on this fact, we propose a novel active selection criterion to evaluate the cost-effectiveness of instance-labeler pairs, which ensures that the selected instance is helpful for improving the classification model, and meanwhile the selected labeler can provide an accurate label for the instance with a relative low cost. Experiments on both UCI and real crowdsourcing data sets demonstrate the superiority of our proposed approach on selecting cost-effective queries.

This paper investigates an important problem in stream mining, i.e., classification under streaming emerging new classes or SENC. The SENC problem can be decomposed into three subproblems: detecting emerging new classes, classifying known classes, and updating models to integrate each new class as part of known classes. The common approach is to treat it as a classification problem and solve it using either a supervised learner or a semi-supervised learner. We propose an alternative approach by using unsupervised learning as the basis to solve this problem. The proposed method employs completely-random trees which have been shown to work well in unsupervised learning and supervised learning independently in the literature. The completely-random trees are used as a single common core to solve all three subproblems: unsupervised learning, supervised learning, and model update on data streams. We show that the proposed unsupervised-learning-focused method often achieves significantly better outcomes than existing classification-focused methods.

User identity linkage across social platforms is an important problem of great research challenge and practical value. In real applications, the task often assumes an extra degree of difficulty by requiring linkage across multiple platforms. While pair-wise user linkage between two platforms, which has been the focus of most existing solutions, provides reasonably convincing linkage, the result depends by nature on the order of platform pairs in execution with no theoretical guarantee on its stability. In this paper, we explore a new concept of ``Latent User Space'' to more naturally model the relationship between the underlying real users and their observed projections onto the varied social platforms, such that the more similar the real users, the closer their profiles in the latent user space. We propose two effective algorithms, a batch model(ULink) and an online model(ULink-On), based on latent user space modelling. Two simple yet effective optimization methods are used for optimizing objective function: the first one based on the constrained concave-convex procedure(CCCP) and the second on accelerated proximal gradient. To our best knowledge, this is the first work to propose a unified framework to address the following two important aspects of the multi-platform user identity linkage problem --- (I) the platform multiplicity and (II) online data generation. We present experimental evaluations on real-world data sets for not only traditional pairwise-platform linkage but also multi-platform linkage. The results demonstrate the superiority of our proposed method over the state-of-the-art ones.