Recent research in federated large language models (LLMs) has primarily focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLMs to small language models (SLMs) at downstream clients. However, a significant gap remains in the simultaneous mutual enhancement of both the server’s LLM and clients’ SLMs. To bridge this gap, we propose FedMKT, a parameter-efficient federated mutual knowledge transfer framework for large and small language models. This framework is designed to adaptively transfer knowledge from the server’s LLM to clients’ SLMs while concurrently enhancing the LLM with clients’ unique domain insights. We facilitate token alignment using minimum edit distance (MinED) and then selective mutual knowledge transfer between client-side SLMs and a server-side LLM, aiming to collectively enhance their performance. Through extensive experiments across three distinct scenarios, we evaluate the effectiveness of FedMKT by utilizing diverse public LLMs and SLMs on a variety of NLP text generation tasks. Empirical results demonstrate that FedMKT simultaneously boosts the performance of both LLMs and SLMs. Our code has been contributed to the FATE open-source project and is now publicly accessible at https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/fedmkt
We investigate how to solve the cross-corpus news recommendation for unseen users in the future. This is a problem where traditional content-based recommendation techniques often fail. Luckily, in real-world recommendation services, some publisher (e.g., Daily news) may have accumulated a large corpus with lots of consumers which can be used for a newly deployed publisher (e.g., Political news). To take advantage of the existing corpus, we propose a transfer learning model (dubbed as TrNews) for news recommendation to transfer the knowledge from a source corpus to a target corpus. To tackle the heterogeneity of different user interests and of different word distributions across corpora, we design a translator-based transfer-learning strategy to learn a representation mapping between source and target corpora. The learned translator can be used to generate representations for unseen users in the future. We show through experiments on real-world datasets that TrNews is better than various baselines in terms of four metrics. We also show that our translator is effective among existing transfer strategies.
Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks. However, mPLM-based methods usually involve two problems: (1) simply fine-tuning may not adapt general-purpose multilingual representations to be task-aware on low-resource languages; (2) ignore how cross-lingual adaptation happens for downstream tasks. To address the issues, we propose a meta graph learning (MGL) method. Unlike prior works that transfer from scratch, MGL can learn to cross-lingual transfer by extracting meta-knowledge from historical CLT experiences (tasks), making mPLM insensitive to low-resource languages. Besides, for each CLT task, MGL formulates its transfer process as information propagation over a dynamic graph, where the geometric structure can automatically capture intrinsic language relationships to explicitly guide cross-lingual transfer. Empirically, extensive experiments on both public and real-world datasets demonstrate the effectiveness of the MGL method.
Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain. The transferred knowledge, however, may unintendedly leak private information of the source domain. For example, an attacker can accurately infer user demographics from their historical purchase provided by a source domain data owner. This paper addresses the above privacy-preserving issue by learning a privacy-aware neural representation by improving target performance while protecting source privacy. The key idea is to simulate the attacks during the training for protecting unseen users’ privacy in the future, modeled by an adversarial game, so that the transfer learning model becomes robust to attacks. Experiments show that the proposed PrivNet model can successfully disentangle the knowledge benefitting the transfer from leaking the privacy.
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method.
Language model is a vital component in modern automatic speech recognition (ASR) systems. Since “one-size-fits-all” language model works suboptimally for conversational speeches, language model adaptation (LMA) is considered as a promising solution for solving this problem. In order to compare the state-of-the-art LMA techniques and systematically demonstrate their effect in conversational speech recognition, we develop a novel toolkit named Chameleon, which includes the state-of-the-art cache-based and topic-based LMA techniques. This demonstration does not only vividly visualize underlying working mechanisms of a variety of the state-of-the-art LMA models but also provide an interface for the user to customize the hyperparameters of them. With this demonstration, the audience can experience the effect of LMA in an interactive and real-time fashion. We wish this demonstration would inspire more research on better language model techniques for ASR.