Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing forgetting data without considering the negative impact this can have on the information of the remaining data, resulting in significant performance degradation after data removal. Although some methods try to repair the performance of remaining data after removal, the forgotten information can also return after repair. Such an issue is due to the intricate intertwining of the forgetting and remaining data. Without adequately differentiating the influence of these two kinds of data on the model, existing algorithms take the risk of either inadequate removal of the forgetting data or unnecessary loss of valuable information from the remaining data. To address this shortcoming, the present study undertakes a causal analysis of the unlearning and introduces a novel framework termed Causal Machine Unlearning (CaMU). This framework adds intervention on the information of remaining data to disentangle the causal effects between forgetting data and remaining data. Then CaMU eliminates the causal impact associated with forgetting data while concurrently preserving the causal relevance of the remaining data. Comprehensive empirical results on various datasets and models suggest that CaMU enhances performance on the remaining data and effectively minimizes the influences of forgetting data. Notably, this work is the first to interpret deep model unlearning tasks from a new perspective of causality and provide a solution based on causal analysis, which opens up new possibilities for future research in deep model unlearning.

A student has designed a handheld'robotic guide dog' to help support people with visual impairments who are unable to house a real assistance animal. Loughborough University design engineer Anthony Camu was inspired to develop the device by responsive virtual reality gaming controllers. Dubbed'Theia' -- after the Titan goddess of light in Greek mythology -- the prototype can replicate the key functions of a real guide dog. The voice-activated device can program quick and safe routes to given destinations using real-time online data -- much like a car's satnav -- and onboard sensors. Force feedback delivered through Theia's handle then helps direct the user -- creating a sensation the designers say is similar to the pull of a guide dog's leash.