More Like this

1. Open-world continual learning: Unifying novelty detection and continual learning

   https://doi.org/10.1016/j.artint.2024.104237  

   Kim, Gyuhak; Xiao, Changnan; Konishi, Tatsuya; Ke, Zixuan; Liu, Bing (January 2025, Artificial Intelligence)

   As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn the new items incrementally to become more and more knowledgeable and powerful. (1) is called novelty detection or out-of-distribution (OOD) detection and (2) is called class incremental learning (CIL), which is a setting of continual learning (CL). In existing research, OOD detection and CIL are regarded as two completely different problems. This paper first provides a theoretical proof that good OOD detection for each task within the set of learned tasks (called closed-world OOD detection) is necessary for successful CIL. We show this by decomposing CIL into two sub-problems: within-task prediction (WP) and task-id prediction (TP), and proving that TP is correlated with closed-world OOD detection. The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good closed-world OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular). We call this traditional CIL the closed-world CIL as it does not detect future OOD data in the open world. The paper then proves that the theory can be generalized or extended to open-world CIL, which is the proposed open-world continual learning, that can perform CIL in the open world and detect future or open-world OOD data. Based on the theoretical results, new CIL methods are also designed, which outperform strong baselines in CIL accuracy and in continual OOD detection by a large margin. 

   more » « less
2. Open-world Learning and Application to Product Classification

   https://doi.org/10.1145/3308558.3313644  

   Xu, Hu; Liu, Bing; Shu, Lei; Yu, P. (May 2019, WWW 2019)

   Classic supervised learning makes the closed-world assumption that the classes seen in testing must have appeared in training. However, this assumption is often violated in real-world applications. For example, in a social media site, new topics emerge constantly and in e-commerce, new categories of products appear daily. A model that cannot detect new/unseen topics or products is hard to function well in such open environments. A desirable model working in such environments must be able to (1) reject examples from unseen classes (not appeared in training) and (2) incrementally learn the new/unseen classes to expand the existing model. This is called open-world learning (OWL). This paper proposes a new OWL method based on meta-learning. The key novelty is that the model maintains only a dynamic set of seen classes that allows new classes to be added or deleted with no need for model re-training. Each class is represented by a small set of training examples. In testing, the meta-classifier only uses the examples of the maintained seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results with e-commerce product classification show that the proposed method is highly effective. 

   more » « less
3. ELSA: Secure Aggregation for Federated Learning with Malicious Actors

   Rathee, Mayank; Shen, Conghao; Wagh, Sameer; Popa, Raluca Ada (January 2023, Proceedings of the IEEE Symposium on Security and Privacy)

   Federated learning (FL) is an increasingly popular approach for machine learning (ML) when the training dataset is highly distributed. Clients perform local training on their datasets and the updates are then aggregated into the global model. Existing protocols for aggregation are either inefficient or don’t consider the case of malicious actors in the system. This is a major barrier to making FL an ideal solution for privacy-sensitive ML applications. In this talk, I will present ELSA, a secure aggregation protocol for FL that breaks this barrier - it is efficient and addresses the existence of malicious actors (clients + servers) at the core of its design. Similar to prior work Prio and Prio+, ELSA provides a novel secure aggregation protocol built out of distributed trust across two servers that keeps individual client updates private as long as one server is honest, defends against malicious clients, and is efficient end-to-end. Compared to prior works, the distinguishing theme in ELSA is that instead of the servers generating cryptographic correlations interactively, the clients act as untrusted dealers of these correlations without compromising the protocol’s security. This leads to a much faster protocol while also achieving stronger security at that efficiency compared to prior work. We introduce new techniques that retain privacy even when a server is malicious at a small added cost of 7-25% in runtime with a negligible increase in communication over the case of a semi-honest server. ELSA improves end-to-end runtime over prior work with similar security guarantees by big margins - single-aggregator RoFL by up to 305x (for the models we consider), and distributed-trust Prio by up to 8x (with up to 16x faster server-side protocol). Additionally, ELSA can be run in a bandwidth-saver mode for clients who are geographically bandwidth-constrained - an important property that is missing from prior works. 

   more » « less
4. ELSA: Secure Aggregation for Federated Learning with Malicious Actors

   Rathee, Mayank; Shen, Conghao; Wagh, Sameer; Popa, Raluca Ada (January 2023, Proceedings of the IEEE Symposium on Security and Privacy)

   Federated learning (FL) is an increasingly popular approach for machine learning (ML) in cases where the training dataset is highly distributed. Clients perform local training on their datasets and the updates are then aggregated into the global model. Existing protocols for aggregation are either inefficient, or don’t consider the case of malicious actors in the system. This is a major barrier in making FL an ideal solution for privacy-sensitive ML applications. We present ELSA, a secure aggregation protocol for FL, which breaks this barrier - it is efficient and addresses the existence of malicious actors at the core of its design. Similar to prior work on Prio and Prio+, ELSA provides a novel secure aggregation protocol built out of distributed trust across two servers that keeps individual client updates private as long as one server is honest, defends against malicious clients, and is efficient end-to-end. Compared to prior works, the distinguishing theme in ELSA is that instead of the servers generating cryptographic correlations interactively, the clients act as untrusted dealers of these correlations without compromising the protocol’s security. This leads to a much faster protocol while also achieving stronger security at that efficiency compared to prior work. We introduce new techniques that retain privacy even when a server is malicious at a small added cost of 7-25% in runtime with negligible increase in communication over the case of semi-honest server. Our work improves end-to-end runtime over prior work with similar security guarantees by big margins - single-aggregator RoFL by up to 305x (for the models we consider), and distributed trust Prio by up to 8x. 

   more » « less
5. Semi-supervised and Incremental VSEARCH for Metagenomic Classification

   https://doi.org/10.1109/SSCI51031.2022.10022184  

   Ozdogan, Emrecan; Fasino, Adriana; Nguyen, Rachel; Sokhansanj, Bahrad; Rosen, Gail; Polikar, Robi (December 2022, 2022 IEEE Symposium Series on Computational Intelligence (SSCI))

   DNA Sequencing of microbial communities from en-vironmental samples generates large volumes of data, which can be analyzed using various bioinformatics pipelines. Unsupervised clustering algorithms are usually an early and critical step in an analysis pipeline, since much of such data are unlabeled, unstructured, or novel. However, curated reference databases that provide taxonomic label information are also increasing and growing, which can help in the classification of sequences, and not just clustering. In this contribution, we report on our progress in developing a semi-supervised approach for genomic clustering algorithms, such as U/VSEARCH. The primary contribution of this approach is the ability to recognize previously seen or unseen novel sequences using an incremental approach: for sequences whose examples were previously seen by the algorithm, the algorithm can predict a correct label. For previously unseen novel sequences, the algorithm assigns a temporary label and then updates that label with a permanent one if/when such a label is established in a future reference database. The incremental learning aspect of the proposed approach provides the additional benefit and capability to process the data continuously as new datasets become available. This functionality is notable as most sequence data processing platforms are static in nature, designed to run on a single batch of data, whose only other remedy to process additional data is to combine the new and old data and rerun the entire analysis. We report our promising preliminary results on an extended 16S rRNA database. 

   more » « less